© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195582
    Prev
    Next
    INDEX
    Explanations

    city 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
    áž
    0.38
     González
    0.37
    koh
    0.37
     tremble
    0.37
     Ade
    0.36
    kab
    0.36
    ξύ
    0.35
    ẋ
    0.35
     Reifen
    0.35
    ξ
    0.35
    POSITIVE LOGITS
     Dar
    0.41
     dar
    0.40
    薩
    0.39
     নন্দ
    0.38
    Dar
    0.38
    UTCDate
    0.38
    トマト
    0.38
     DAR
    0.38
     surrendered
    0.38
     Waterford
    0.37
    Activations Density 0.000%

    No Known Activations