© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10672
    Prev
    Next
    INDEX
    Explanations

    words and phrases that can imply a story or event is taking place.

    oai_token-act-pair · gemini-2.0-flash

    proving something

    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>
    -0.70
    ConstraintMaker
    -0.68
    ArrowToggle
    -0.66
    CodeAttribute
    -0.66
    IntoConstraints
    -0.65
     ModelExpression
    -0.63
     lenker
    -0.63
     صوتيه
    -0.63
    twimg
    -0.62
     Bioaccumulative
    -0.62
    POSITIVE LOGITS
    TypedDataSet
    0.43
     maksud
    0.42
     määrä
    0.42
    oky
    0.41
     case
    0.40
    Сообщение
    0.40
    SharedDtor
    0.38
     ứng
    0.36
     смысле
    0.36
     AppBundle
    0.36
    Activations Density 0.334%

    No Known Activations