© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4020
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -0.94
     Efq
    -0.90
     ſtate
    -0.90
     faſt
    -0.89
     ſmall
    -0.89
     auffi
    -0.87
    intios
    -0.85
     houſe
    -0.85
     purpoſe
    -0.85
     ſtand
    -0.84
    POSITIVE LOGITS
    *
    0.61
    ia
    0.56
    MigrationBuilder
    0.55
    <strong>
    0.53
    1
    0.53
    t
    0.53
    ****************
    0.53
    to
    0.52
    Apart
    0.52
    She
    0.51
    Activations Density 0.660%

    No Known Activations