© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12203
    Prev
    Next
    INDEX
    Explanations

    lines of code documentation

    oai_token-act-pair · gemini-2.0-flash

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    featureID
    -0.59
    Completion
    -0.48
     coû
    -0.48
     kuten
    -0.47
     financière
    -0.47
     complètes
    -0.47
     @"/
    -0.46
    ModelBuilder
    -0.45
     Kreise
    -0.45
     Stevens
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.94
     صوتيه
    0.73
     resourceCulture
    0.63
     insuffisamment
    0.62
     estekak
    0.61
     Meksiku
    0.59
    AndEndTag
    0.57
     leſs
    0.56
    Rüyada
    0.56
     فريبيس
    0.56
    Activations Density 0.078%

    No Known Activations