© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    a mix of pronouns, negations, and words related to family and social dynamics, possibly indicating recognition of interpersonal relationships and concerns.

    oai_token-act-pair · gemini-2.0-flash

    words related to decision-making or opinion formation

    np_token-act-pair-logits · gpt-4o-mini

    Words related to thinking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.85
     سكانية
    -0.82
    Personendaten
    -0.81
    RegressionTest
    -0.78
     الحره
    -0.76
    OGND
    -0.76
    SourceChecksum
    -0.75
    msgTypes
    -0.74
     للاسماء
    -0.74
    abetes
    -0.72
    POSITIVE LOGITS
     become
    0.41
     deem
    0.40
     think
    0.38
    Become
    0.38
     compt
    0.37
    認為
    0.37
     peg
    0.36
     shun
    0.36
     chi
    0.36
    摩
    0.36
    Activations Density 3.342%

    No Known Activations