© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14398
    Prev
    Next
    INDEX
    Explanations

    Java and Kotlin code syntax, identifying packages, imports, classes, and object instantiation.

    oai_token-act-pair · gemini-2.0-flash

    package

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    corrência
    -0.39
     pungkasnya
    -0.30
    hæng
    -0.29
     ModelExpression
    -0.29
    apkamer
    -0.28
    eens
    -0.28
    hånd
    -0.28
    centaje
    -0.28
    InputBorder
    -0.28
    چار
    -0.28
    POSITIVE LOGITS
    IsContent
    0.79
     autorytatywna
    0.72
     חיצוניים
    0.71
    Spoljašnje
    0.70
     estimés
    0.66
     Flare
    0.66
    AutoField
    0.65
     незавершена
    0.65
     typelib
    0.64
    blaze
    0.63
    Activations Density 7.724%

    No Known Activations