© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202858
    Prev
    Next
    INDEX
    Explanations

    aggravated assault, severe, worse

    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_12_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
    /
    0.61
    、
    0.54
     at
    0.51
    )。
    0.47
    (
    0.46
    极端
    0.46
     Worse
    0.45
     drafts
    0.44
    )");
    0.43
    こ
    0.43
    POSITIVE LOGITS
    ğı
    0.63
    direito
    0.62
     guia
    0.59
    bola
    0.58
     broj
    0.58
     cadeia
    0.57
    benzoimidazol
    0.55
     mensagem
    0.55
     ذہ
    0.55
    Результа
    0.54
    Activations Density 0.005%

    No Known Activations