© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31820
    Prev
    Next
    INDEX
    Explanations

    were injured or arrested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enche
    0.25
    othe
    0.24
    obb
    0.23
     echo
    0.23
     ata
    0.22
    inchi
    0.22
    dob
    0.22
    笊
    0.22
    িঝ
    0.22
    incs
    0.22
    POSITIVE LOGITS
     separations
    0.25
     Gedanken
    0.23
     boundedness
    0.23
    登山
    0.23
     ഗവേഷ
    0.23
     група
    0.22
    '||
    0.22
     hospitalized
    0.22
     दक्षता
    0.22
     grasp
    0.22
    Activations Density 0.003%

    No Known Activations