© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    phrases that include words like "still", "magic", and words indicating small amounts

    oai_token-act-pair · gemini-2.0-flash

    Uncertainty/tentativeness

    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
    ГЛА
    -0.47
    <bos>
    -0.46
    Gambas
    -0.45
    protoimpl
    -0.43
    Примечания
    -0.41
    clyde
    -0.40
    lüğ
    -0.40
     car
    -0.40
     Prior
    -0.39
    endregion
    -0.39
    POSITIVE LOGITS
    PreferredItem
    0.73
     alimentaria
    0.65
    explique
    0.65
    ')):
    0.65
     otomatig
    0.65
     myſelf
    0.64
    帖最后由
    0.63
    LookAnd
    0.63
    numerusform
    0.63
    zeczytaj
    0.61
    Activations Density 0.317%

    No Known Activations