© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33655
    Prev
    Next
    INDEX
    Explanations

    hate crime investigation

    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_3_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
    اً
    0.84
    م
    0.71
    ના
    0.70
    M
    0.63
    et
    0.62
    se
    0.62
    Mode
    0.61
    Dist
    0.61
    d
    0.61
    مان
    0.60
    POSITIVE LOGITS
     i
    0.72
     план
    0.66
     наре
    0.65
     נ
    0.63
     все
    0.62
    (
    0.62
     руки
    0.61
     обеспечи
    0.60
     crates
    0.60
     вклю
    0.59
    Activations Density 0.001%

    No Known Activations