© 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. 8747
    Prev
    Next
    INDEX
    Explanations

    colon-separated digit pairs.

    oai_token-act-pair · gemini-2.0-flash

    :

    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
     okuyayım
    -0.57
     >=",
    -0.56
    iastes
    -0.55
    Tembelea
    -0.55
     Мексичка
    -0.54
     intégr
    -0.54
     مرئيه
    -0.52
    Gweler
    -0.51
    Geplaatst
    -0.51
    ivably
    -0.51
    POSITIVE LOGITS
    ListItemIcon
    0.50
    HasForeignKey
    0.48
    SharedCtor
    0.47
    AnimationsModule
    0.47
    DatabaseError
    0.46
    //
    0.46
    TypedDataSet
    0.45
     defaults
    0.44
     confiscation
    0.44
     Ursachen
    0.44
    Activations Density 1.136%

    No Known Activations