© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175512
    Prev
    Next
    INDEX
    Explanations

    fine

    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_50_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
    isis
    0.39
     kep
    0.35
    ICKEL
    0.35
    şık
    0.35
    肃
    0.35
     Kep
    0.34
     suffixes
    0.34
     fiscal
    0.33
    etically
    0.33
    首
    0.33
    POSITIVE LOGITS
    Fine
    3.08
     fine
    3.06
     Fine
    2.94
    fine
    2.83
     FINE
    2.64
    FINE
    2.59
    细
    2.11
     fines
    2.09
    細
    2.08
     फाइन
    2.06
    Activations Density 0.001%

    No Known Activations