© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tag href attributes

    oai_token-act-pair · gemini-2.0-flash

    HTML ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DockStyle
    -0.91
    CPtr
    -0.64
    NOPQRST
    -0.63
    +#+
    -0.62
    quelize
    -0.60
    Configurer
    -0.59
    IContainer
    -0.59
     jScrollPane
    -0.58
     /*#__
    -0.56
    migrationBuilder
    -0.56
    POSITIVE LOGITS
     crainte
    0.48
    iesc
    0.45
    ThroughAttribute
    0.45
     fald
    0.45
     perchè
    0.44
     récupération
    0.44
    ipt
    0.44
     stabilité
    0.43
    fab
    0.43
    慎
    0.43
    Activations Density 0.090%

    No Known Activations