© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156360
    Prev
    Next
    INDEX
    Explanations

    malice, trance, severance, veracity

    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_2_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
    ী
    1.30
    های
    1.23
    ر
    1.23
    ור
    1.21
    ل
    1.21
    ות
    1.18
    ש
    1.17
    <h2>
    1.13
    .
    1.11
    न
    1.10
    POSITIVE LOGITS
    在
    1.16
    大脑
    1.13
    大
    1.13
    AN
    1.11
    0
    1.05
    EN
    1.03
    。
    1.03
    AL
    1.02
     但
    1.02
    ។
    1.02
    Activations Density 0.037%

    No Known Activations