© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11749
    Prev
    Next
    INDEX
    Explanations

    words and symbols in a university newspaper

    oai_token-act-pair · gemini-2.0-flash

    SSS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    antaranya
    -0.54
     nahilalakip
    -0.51
    Билгалдахарш
    -0.49
    IndentedString
    -0.46
    Palmarès
    -0.45
    fjspx
    -0.45
    Дереккөздер
    -0.44
     فريبيس
    -0.43
    Տես
    -0.42
    ์ตูน
    -0.42
    POSITIVE LOGITS
    multicolumn
    0.64
    didSet
    0.56
     EdgeInsets
    0.54
    rcParams
    0.54
    StatusBadRequest
    0.52
     StatefulWidget
    0.51
    LIOT
    0.49
     NDEBUG
    0.48
    desh
    0.48
     BorderRadius
    0.48
    Activations Density 15.171%

    No Known Activations