© 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. 227483
    Prev
    Next
    INDEX
    Explanations

    Gini Coefficient or Gini Importance

    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
    ン
    1.20
    ان
    1.15
    ন
    1.13
    t
    1.13
    리
    1.09
    ル
    1.07
    V
    1.06
    ר
    1.06
    ر
    1.05
    ת
    1.05
    POSITIVE LOGITS
    '
    1.15
    ).
    0.95
    ig
    0.94
    for
    0.93
    }
    0.88
    ier
    0.87
    od
    0.85
     Página
    0.84
    %
    0.84
     **
    0.82
    Activations Density 0.000%

    No Known Activations