© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6174
    Prev
    Next
    INDEX
    Explanations

    content related to court cases and politicians' activity.

    oai_token-act-pair · gemini-2.0-flash

    legal/political events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    __*/
    -0.73
     समीक्षाओं
    -0.68
    RectangleBorder
    -0.66
    исленность
    -0.65
     useAppContext
    -0.65
     Lumpur
    -0.64
    TintMode
    -0.63
    GIVEREF
    -0.63
     protoimpl
    -0.61
    Географи
    -0.61
    POSITIVE LOGITS
    ężczy
    0.46
     Male
    0.42
     słu
    0.42
     Jacob
    0.42
    كذا
    0.41
     Rama
    0.40
     rama
    0.39
    Grado
    0.39
     National
    0.39
     national
    0.39
    Activations Density 0.497%

    No Known Activations