© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12638
    Prev
    Next
    INDEX
    Explanations

    words and titles used when giving testimony or pertaining to court proceedings

    oai_token-act-pair · gemini-2.0-flash

    Captain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    W
    -0.53
    R
    -0.45
    w
    -0.45
    F
    -0.43
    In
    -0.41
    <u>
    -0.40
    Ter
    -0.39
    –
    -0.38
    </strong>
    -0.38
    J
    -0.38
    POSITIVE LOGITS
     виправивши
    1.28
     Monfieur
    1.18
    CloseOperation
    1.13
     Efq
    1.12
     defaultstate
    1.09
    extAlignment
    1.06
    parsedMessage
    1.05
    +#+#
    1.04
    NUMX
    1.01
    ReusableCell
    1.01
    Activations Density 7.170%

    No Known Activations