© 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. 2387
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons of different objects

    oai_token-act-pair · gemini-2.0-flash

    terms related to biological or regulatory concepts

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

    technical and scientific writing

    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
     similar
    -1.30
    similar
    -1.12
     Similar
    -1.10
    Similar
    -1.09
     SIMILAR
    -0.96
     liknande
    -0.95
     ähnlichen
    -0.93
     similaire
    -0.91
     similaires
    -0.85
     podob
    -0.85
    POSITIVE LOGITS
     at
    0.55
     通販
    0.54
    loroethene
    0.52
     Bioaccumulative
    0.50
    BorderFactory
    0.50
    Véxase
    0.49
     une
    0.48
    يمة
    0.48
     subject
    0.47
    cyjna
    0.47
    Activations Density 3.021%

    No Known Activations