© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    instances of something serving as something else.

    oai_token-act-pair · gemini-2.0-flash

    as

    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
    RectangleBorder
    -0.82
    ########.
    -0.80
    VersionUID
    -0.76
    NUMX
    -0.61
    GPP
    -0.60
    hematics
    -0.58
    OrNil
    -0.58
    }{*}{}
    -0.57
    úgó
    -0.56
    oleic
    -0.56
    POSITIVE LOGITS
     للاسماء
    0.56
     Corintios
    0.49
     kaynağından
    0.47
     reserved
    0.45
     Parry
    0.45
     ویکی‌پدی
    0.43
    AnimationsModule
    0.42
    outon
    0.42
    tagHelperRunner
    0.42
     réservés
    0.42
    Activations Density 9.846%

    No Known Activations