© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1964
    Prev
    Next
    INDEX
    Explanations

    words related to gaining entry or obtaining goods

    oai_token-act-pair · gemini-2.0-flash

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     access
    -2.95
     Access
    -2.66
    access
    -2.66
    Access
    -2.58
     ACCESS
    -2.14
     acesso
    -2.02
     acceso
    -2.02
    ACCESS
    -1.99
     accesses
    -1.92
     accessing
    -1.91
    POSITIVE LOGITS
    出版年
    0.50
    帖最后由
    0.48
     Others
    0.47
    IsContent
    0.47
     pinulongan
    0.42
    Koordinaten
    0.42
     /*#__
    0.42
    :+:
    0.42
    ItemBackground
    0.42
    Requirement
    0.41
    Activations Density 11.695%

    No Known Activations