© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175383
    Prev
    Next
    INDEX
    Explanations

    controller, operators, panels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     বৈঠকে
    0.44
    深圳
    0.41
     stärker
    0.41
    ımda
    0.41
    赢
    0.40
    ﻲ
    0.40
     %>',
    0.40
    采访
    0.39
     상승
    0.39
    фай
    0.39
    POSITIVE LOGITS
    aduras
    0.47
     Gran
    0.47
    ಡೆ
    0.46
     ades
    0.45
    ोला
    0.44
    ګ
    0.44
     למ
    0.42
    ableConcept
    0.42
     Gregorian
    0.42
    枴
    0.42
    Activations Density 0.000%

    No Known Activations