© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    references to eras and generations

    oai_token-act-pair · gemini-2.0-flash

    age

    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
     dimaksud
    -0.47
    cdef
    -0.46
     Arrondissement
    -0.46
    лото
    -0.45
     дово
    -0.43
    ternos
    -0.43
     internos
    -0.43
     pâtes
    -0.42
    <eos>
    -0.41
    grupp
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.95
    VersionUID
    0.88
    bootstrapcdn
    0.73
    AndEndTag
    0.72
     '\\;'
    0.69
     referenties
    0.68
     समीक्षक
    0.68
    Geplaatst
    0.68
     оригіналу
    0.65
    Démographie
    0.65
    Activations Density 0.125%

    No Known Activations