© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7067
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and grammatical structures indicating possibility, obligation, and intended action.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    LookAnd
    -0.82
     adopt
    -0.66
     الرياضيه
    -0.61
     Adop
    -0.61
    mybatisplus
    -0.60
     treat
    -0.59
    adopt
    -0.59
    Adopt
    -0.57
     Treat
    -0.55
     autorytatywna
    -0.55
    POSITIVE LOGITS
    WebElementEntity
    0.64
    Tembelea
    0.56
    存于互联网档案馆
    0.56
    toMatchSnapshot
    0.53
     وتسجيلات
    0.53
     trajets
    0.51
     scio
    0.49
    providedIn
    0.49
     secco
    0.47
     ModelExpression
    0.45
    Activations Density 5.964%

    No Known Activations