© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    names, places, and coded identifiers

    oai_token-act-pair · gemini-2.0-flash

    William

    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
    Према
    -0.68
    präsident
    -0.60
     mass
    -0.54
    dexter
    -0.52
    rador
    -0.51
    acherous
    -0.47
    knię
    -0.45
     gasolina
    -0.45
     embry
    -0.45
     objec
    -0.45
    POSITIVE LOGITS
     lenker
    0.65
    TagMode
    0.64
     poveznice
    0.59
     Numerade
    0.59
     Référence
    0.56
     kasarigan
    0.56
     ModelExpression
    0.54
    quelize
    0.53
    :✨
    0.51
    Personensuche
    0.51
    Activations Density 0.093%

    No Known Activations