© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13844
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code blocks

    oai_token-act-pair · gemini-2.0-flash

    },

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Билгалдахарш
    -0.90
    principalColumn
    -0.82
     surla
    -0.82
     nahilalakip
    -0.79
    expandindo
    -0.78
     mergeFrom
    -0.77
    SequentialGroup
    -0.74
    はじめに
    -0.73
     članak
    -0.69
    windowFixed
    -0.68
    POSITIVE LOGITS
     Invasion
    0.56
     amet
    0.56
    Invasion
    0.49
     Stam
    0.46
     arches
    0.45
    Fcn
    0.45
     baton
    0.44
    keydown
    0.43
     cleats
    0.43
    noscript
    0.43
    Activations Density 5.661%

    No Known Activations