© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77218
    Prev
    Next
    INDEX
    Explanations

    Sal / Sally

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    panelMenuList
    0.35
    瓢
    0.34
     shrink
    0.33
    ComponentModel
    0.33
    FET
    0.33
    হইল
    0.32
    scan
    0.32
     చంద్ర
    0.32
     वर्गों
    0.32
    ጾ
    0.31
    POSITIVE LOGITS
    Sal
    3.14
     Sal
    3.06
     SAL
    2.95
     sal
    2.91
    sal
    2.86
    SAL
    2.86
     살
    2.31
     Sally
    2.31
    Sally
    2.30
     sali
    2.27
    Activations Density 0.011%

    No Known Activations