© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33271
    Prev
    Next
    INDEX
    Explanations

    Prosecco, sysctl, or prostitution

    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
    Negative Logits
    ۸
    0.72
     민
    0.70
    s
    0.69
     тала
    0.68
    a
    0.66
    암
    0.66
     bairro
    0.65
    specific
    0.64
    ೮
    0.63
     פור
    0.62
    POSITIVE LOGITS
    il
    1.02
    т
    0.88
    ب
    0.86
    j
    0.79
    ные
    0.73
    et
    0.72
    ak
    0.72
    ing
    0.71
    ت
    0.70
    ą
    0.70
    Activations Density 0.011%

    No Known Activations