© 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. 8876
    Prev
    Next
    INDEX
    Explanations

    numerical data, and mentions of specific chemicals or companies.

    oai_token-act-pair · 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
     truly
    -0.44
     gelegen
    -0.42
     really
    -0.41
    getMin
    -0.38
    śred
    -0.38
     podido
    -0.37
     Evolution
    -0.37
    fang
    -0.36
    VY
    -0.36
     generally
    -0.36
    POSITIVE LOGITS
     الحره
    0.87
    InSection
    0.86
    UnsafeEnabled
    0.80
    ########.
    0.80
     كومونز
    0.79
    NewUrlParser
    0.79
    WebVitals
    0.78
    (!__
    0.75
     EconPapers
    0.73
     Италијани
    0.73
    Activations Density 1.578%

    No Known Activations