© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44125
    Prev
    Next
    INDEX
    Explanations

    me

    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_3_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
     को
    0.73
    ک
    0.73
     t
    0.70
    มห
    0.70
     culminating
    0.68
    لای
    0.68
     in
    0.67
    ব
    0.67
     bystanders
    0.65
     are
    0.64
    POSITIVE LOGITS
     كات
    0.66
     cataly
    0.66
    beitung
    0.62
     بيان
    0.62
    أ
    0.62
     نسخة
    0.61
     مكان
    0.61
     prefque
    0.61
    0.60
     كامل
    0.60
    Activations Density 0.008%

    No Known Activations