© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 25025
    Prev
    Next
    INDEX
    Explanations

    dark hair

    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_56_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
     fri
    1.49
    fri
    1.03
     Fri
    1.02
    Fri
    1.00
     FRI
    0.88
     m
    0.83
     string
    0.69
    string
    0.69
    FRI
    0.65
    Tang
    0.62
    POSITIVE LOGITS
    ሐ
    0.38
    ]}'
    0.37
     Vermö
    0.36
     SWT
    0.35
    egraphics
    0.35
     Evan
    0.35
    يش
    0.34
    LX
    0.34
     Vieux
    0.34
     commod
    0.34
    Activations Density 0.031%

    No Known Activations