© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205885
    Prev
    Next
    INDEX
    Explanations

    obscene/explicit content description

    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_6_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
    s
    1.63
    sk
    1.16
    v
    1.16
    ur
    1.01
    ch
    1.01
    in
    0.99
    k
    0.97
    sa
    0.96
    ta
    0.96
    sen
    0.96
    POSITIVE LOGITS
    كتب
    1.08
     especiales
    0.99
    Т
    0.92
     étude
    0.91
    كمل
    0.91
    Пред
    0.91
     accentuate
    0.91
    وفي
    0.91
     décerné
    0.91
    ظيم
    0.89
    Activations Density 0.000%

    No Known Activations