© 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. 77149
    Prev
    Next
    INDEX
    Explanations

    In media res

    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
     Fletcher
    0.47
    ഫി
    0.44
    യു
    0.44
     spotlight
    0.41
     Fle
    0.39
     Fleece
    0.39
    軒
    0.39
    Fle
    0.38
    DejaVu
    0.38
     fistule
    0.38
    POSITIVE LOGITS
    хів
    0.40
    "--
    0.37
    èbre
    0.36
    ܪ
    0.36
    мона
    0.36
    acirc
    0.36
    Sadly
    0.36
    LONG
    0.35
    льтра
    0.35
     ত্রিপ
    0.35
    Activations Density 0.000%

    No Known Activations