© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198219
    Prev
    Next
    INDEX
    Explanations

    abolition / abol / bol

    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_4_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
    I
    1.00
    :
    1.00
    ',
    0.92
     on
    0.89
    ha
    0.89
    の名前
    0.87
    abilir
    0.85
    ada
    0.85
    ya
    0.84
    ۴
    0.83
    POSITIVE LOGITS
    ي
    1.16
    는
    1.14
    ى
    1.08
    ية
    1.05
    يق
    1.00
    يّ
    0.96
    <0x80>
    0.96
    ið
    0.93
    но
    0.92
    0
    0.86
    Activations Density 0.001%

    No Known Activations