© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6774
    Prev
    Next
    INDEX
    Explanations

    words used in a courtroom setting when giving testimony

    oai_token-act-pair · gemini-2.0-flash

    late or early

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     fieldNum
    -0.73
    awtextra
    -0.72
    ConstraintMaker
    -0.65
    WebServlet
    -0.59
     تانيه
    -0.59
    PerformLayout
    -0.58
    GTCX
    -0.58
    SequentialGroup
    -0.57
    uxxxx
    -0.56
    apunov
    -0.56
    POSITIVE LOGITS
     late
    0.89
    late
    0.76
     early
    0.73
    early
    0.70
     Late
    0.69
    Late
    0.68
     LATE
    0.67
     later
    0.62
     Early
    0.61
    closing
    0.59
    Activations Density 1.278%

    No Known Activations