© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204002
    Prev
    Next
    INDEX
    Explanations

    check

    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_6_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
    ری
    0.83
    ے
    0.82
    ان
    0.80
    inę
    0.77
    یم
    0.73
     synagogues
    0.72
     اکاؤن
    0.72
    お金
    0.70
    یل
    0.69
    ма
    0.68
    POSITIVE LOGITS
     كه
    0.91
     في
    0.86
    elijke
    0.86
    _
    0.82
     جي
    0.80
     of
    0.75
     الكبير
    0.74
     welke
    0.73
    zeit
    0.72
     كبير
    0.72
    Activations Density 0.010%

    No Known Activations