© 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. 134178
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    ირო
    0.46
     필
    0.43
    怡
    0.41
     monolith
    0.40
     كده
    0.39
    ocell
    0.38
    responds
    0.37
    UTTON
    0.37
    ডের
    0.35
     이용해서
    0.35
    POSITIVE LOGITS
    山
    0.41
     Mountain
    0.40
     Vig
    0.40
     Aan
    0.39
     জমে
    0.38
     Alaska
    0.38
    ulum
    0.37
    줍
    0.37
    ospel
    0.37
    Mountain
    0.37
    Activations Density 0.000%

    No Known Activations