© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12705
    Prev
    Next
    INDEX
    Explanations

    the phrase "so on" or "much more"

    oai_token-act-pair · gemini-2.0-flash

    quantity or continuation

    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
    rawDesc
    -0.53
     Pum
    -0.53
    Ok
    -0.51
     Soro
    -0.50
     PPR
    -0.50
     Hessian
    -0.49
    offsetof
    -0.49
    twimg
    -0.48
     BOP
    -0.48
     onBind
    -0.48
    POSITIVE LOGITS
    <?
    0.56
     >=",
    0.52
    pædia
    0.52
    UnknownFieldSet
    0.50
    TProtocol
    0.49
     विश्वसनीयता
    0.49
     ويكيميديا
    0.48
    itzende
    0.47
    Personensuche
    0.47
     الاطلاع
    0.47
    Activations Density 0.147%

    No Known Activations