© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    technical or abbreviation riddled language within text, often including parenthetical remarks and numbered lists.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    <bos>
    -0.58
    ंदीखरीदारी
    -0.57
    出版年
    -0.56
    offsetof
    -0.52
    Sqft
    -0.52
    .'”
    -0.51
     TestBed
    -0.49
    tagext
    -0.49
    uests
    -0.48
     мәкал
    -0.48
    POSITIVE LOGITS
     /\.
    0.70
    ViewFeatures
    0.61
     Waray
    0.51
    ]._
    0.49
    Géographie
    0.48
    ($__
    0.46
     OTHERWISE
    0.46
     sanitaires
    0.46
    انظر
    0.46
    bootstrapcdn
    0.46
    Activations Density 1.151%

    No Known Activations