© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208092
    Prev
    Next
    INDEX
    Explanations

    technical subjects and applications

    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_10_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
    MDET
    0.59
    コーヒー
    0.52
    乸
    0.52
    誣
    0.52
    雓
    0.51
    掄
    0.51
    賽
    0.50
     السابع
    0.49
    testAvg
    0.49
    渙
    0.49
    POSITIVE LOGITS
     Text
    0.58
    ard
    0.57
     a
    0.56
    ina
    0.55
    Text
    0.55
     locations
    0.53
    aram
    0.50
     cable
    0.49
     an
    0.49
    ud
    0.49
    Activations Density 0.000%

    No Known Activations