© 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. 232436
    Prev
    Next
    INDEX
    Explanations

    Ghost in the Shell

    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
    '};
    0.97
    يد
    0.91
    이스
    0.83
     É
    0.81
     يُ
    0.80
     实现
    0.78
     ي
    0.76
     سي
    0.75
    '=>$
    0.75
     việc
    0.75
    POSITIVE LOGITS
    the
    1.23
    కు
    1.20
    지
    1.20
    ों
    1.11
    ม
    1.01
    ם
    1.01
    ной
    0.95
    ных
    0.93
    The
    0.92
    มะ
    0.91
    Activations Density 0.000%

    No Known Activations