© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    numbers or number-related words in a technical or scientific context

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ometries
    -0.59
    ergies
    -0.53
    colates
    -0.53
     vectors
    -0.52
     Syrie
    -0.52
    lections
    -0.52
     diagonals
    -0.50
    selectors
    -0.50
    AsUp
    -0.49
    vectors
    -0.49
    POSITIVE LOGITS
    /*
    0.63
    kloped
    0.58
    ScopeManager
    0.57
    migrationBuilder
    0.57
    webElementXpaths
    0.56
    Chham
    0.53
    ArgsConstructor
    0.51
    UserScript
    0.50
    yntaxException
    0.50
    WebElementEntity
    0.50
    Activations Density 19.129%

    No Known Activations