© 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. 8803
    Prev
    Next
    INDEX
    Explanations

    words and phrases of subjective praise and enthusiasm, especially when combined with prepositions.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

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

    possessive pronouns

    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
     company
    -1.00
    彼らは
    -0.85
    Company
    -0.81
    company
    -0.78
     Company
    -0.77
     họ
    -0.73
    THEY
    -0.69
    They
    -0.67
    selves
    -0.66
     They
    -0.66
    POSITIVE LOGITS
     it
    1.24
     its
    1.09
     your
    0.81
     seu
    0.81
     sua
    0.77
     his
    0.76
     seus
    0.72
     suas
    0.69
     svoje
    0.66
     그것
    0.65
    Activations Density 6.761%

    No Known Activations