© 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. 4204
    Prev
    Next
    INDEX
    Explanations

    the word "functional," sometimes in conjunction with related terms like "molecular."

    oai_token-act-pair · gemini-2.0-flash

    functional

    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
     مشين
    -0.88
    帖最后由
    -0.78
     scolaires
    -0.78
    Дереккөздер
    -0.77
     humain
    -0.73
    waiter
    -0.73
     Оно
    -0.72
     umane
    -0.72
    ✨:
    -0.71
     spéciaux
    -0.71
    POSITIVE LOGITS
    ioutil
    0.66
    .
    0.65
    SPATH
    0.59
     Immutable
    0.57
     useHistory
    0.55
     ([]
    0.54
    ublik
    0.52
    semibold
    0.52
    datal
    0.52
     incoming
    0.51
    Activations Density 1.335%

    No Known Activations