© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12074
    Prev
    Next
    INDEX
    Explanations

    code formatting and structure

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements or function names

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    amaño
    -0.61
    IntoConstraints
    -0.56
    ruff
    -0.48
    最快更新
    -0.47
     ligiloj
    -0.47
     CGPoint
    -0.46
    Kanpo
    -0.45
     forState
    -0.45
    setVerticalGroup
    -0.45
     كومونز
    -0.44
    POSITIVE LOGITS
    Â
    0.53
    infall
    0.50
    principalTable
    0.48
     GenerationType
    0.48
    autorest
    0.48
    lidge
    0.48
    WithIdentifier
    0.48
     avance
    0.48
    rungen
    0.47
    igator
    0.47
    Activations Density 0.332%

    No Known Activations