© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9386
    Prev
    Next
    INDEX
    Explanations

    mentions of innings in baseball

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    enumii
    -0.77
    脚注の使い方
    -0.75
    CppMethod
    -0.68
    таратура
    -0.68
     noDo
    -0.66
     المعيارى
    -0.63
    +#+#
    -0.63
     Audiodateien
    -0.61
    aarrggbb
    -0.60
     ExecuteAsync
    -0.59
    POSITIVE LOGITS
    δος
    0.50
     Offisielt
    0.50
    InvalidProtocol
    0.47
    dailymail
    0.44
     هزار
    0.43
     vendu
    0.42
    ésultat
    0.41
    insatz
    0.41
     interval
    0.40
     السياسية
    0.40
    Activations Density 0.527%

    No Known Activations