© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3001
    Prev
    Next
    INDEX
    Explanations

    words that contain "form" relating to performance or execution, and possibly "for"

    oai_token-act-pair · gemini-2.0-flash

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    InputBorder
    -0.85
     utafitiHapana
    -0.80
    RenderAtEndOf
    -0.76
    apunov
    -0.68
    ]^{-
    -0.68
    LogFactory
    -0.66
    basicConfig
    -0.66
    knex
    -0.65
    جغرافيا
    -0.65
    writeFieldEnd
    -0.63
    POSITIVE LOGITS
     performance
    1.44
     performances
    1.34
    performance
    1.34
     Performance
    1.27
    Performance
    1.26
     Performances
    1.23
    PERFORMANCE
    1.21
     perform
    1.20
     PERFORMANCE
    1.20
    Performances
    1.16
    Activations Density 1.109%

    No Known Activations