© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51734
    Prev
    Next
    INDEX
    Explanations

    team names, scores, and outcomes

    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_30_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
    ȟ
    0.24
    ge
    0.23
    合物
    0.23
    Volt
    0.23
    Interview
    0.22
     ContentValues
    0.22
     ध्वस्त
    0.21
    ંત
    0.21
     expressed
    0.21
    arente
    0.21
    POSITIVE LOGITS
     കോണ്‍ഗ്ര
    0.26
     Oleg
    0.26
     vec
    0.25
    崗
    0.25
     쿠
    0.24
     Liquor
    0.24
    jø
    0.24
    奎
    0.24
     Дар
    0.23
    Фа
    0.23
    Activations Density 0.000%

    No Known Activations