© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8303
    Prev
    Next
    INDEX
    Explanations

    code syntax and code documentation.

    oai_token-act-pair · gemini-2.0-flash

    colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     covered
    -1.41
    Covered
    -1.18
     Covered
    -1.17
    covered
    -1.15
     bases
    -0.95
     COVER
    -0.90
     coverage
    -0.82
     cubierto
    -0.82
     couverte
    -0.78
     cover
    -0.75
    POSITIVE LOGITS
     HasFactory
    0.66
     esternos
    0.65
    RectangleBorder
    0.63
    GOTREF
    0.63
    AddTagHelper
    0.61
     Infórmanos
    0.60
     opérés
    0.56
    softc
    0.54
    WebElementEntity
    0.54
    expandindo
    0.54
    Activations Density 1.516%

    No Known Activations