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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6338
    Prev
    Next
    INDEX
    Explanations

    Dataset classes

    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_40_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
     мат
    0.40
    标
    0.39
     Nob
    0.37
     бли
    0.37
     batter
    0.37
     blaze
    0.37
     rubs
    0.37
     singleton
    0.37
     norm
    0.36
     நு
    0.35
    POSITIVE LOGITS
     Six
    0.46
    Six
    0.45
    Eight
    0.43
     बांधकाम
    0.41
    وش
    0.39
     六
    0.39
    六
    0.38
    oinen
    0.38
    오
    0.37
    皖
    0.37
    Activations Density 0.004%

    No Known Activations