© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37491
    Prev
    Next
    INDEX
    Explanations

    Clara

    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_57_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
    row
    0.74
    Row
    0.67
     row
    0.67
    ROW
    0.66
    行
    0.64
     rows
    0.60
     Row
    0.60
    rows
    0.58
     ROW
    0.53
     행
    0.52
    POSITIVE LOGITS
     EMERG
    0.39
    idik
    0.38
     Hallmark
    0.38
    Ϟ
    0.38
     Trich
    0.38
    Runnable
    0.38
     রসের
    0.38
     Emerging
    0.36
     larva
    0.36
    රු
    0.36
    Activations Density 0.003%

    No Known Activations