© 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. 126308
    Prev
    Next
    INDEX
    Explanations

    violence prevention programs

    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
    것
    0.77
    מ
    0.68
    h
    0.62
    その
    0.60
    v
    0.60
    ট
    0.59
     }}=\
    0.59
     중심
    0.59
     are
    0.58
     tingling
    0.58
    POSITIVE LOGITS
    quire
    0.71
    ي
    0.65
    storage
    0.64
    hiyan
    0.64
     апре
    0.64
     raffin
    0.64
    ьев
    0.64
    an
    0.63
    lier
    0.63
    kých
    0.63
    Activations Density 0.000%

    No Known Activations