© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7999
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    references to figures/tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ネート
    -0.42
    Filmografie
    -0.38
     precisamente
    -0.38
     इससे
    -0.36
    ifikationer
    -0.35
    CodeAnalysis
    -0.35
    ulants
    -0.34
    BagLayout
    -0.33
    Demografia
    -0.33
     factura
    -0.33
    POSITIVE LOGITS
    fjspx
    0.83
    astify
    0.78
    WithIOException
    0.73
    UserScript
    0.71
    parsedMessage
    0.70
    enumi
    0.67
    ISupport
    0.66
    webElementXpaths
    0.65
    RetentionPolicy
    0.65
    LookAnd
    0.64
    Activations Density 6.201%

    No Known Activations