© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129877
    Prev
    Next
    INDEX
    Explanations

    thrilling penalty shootout

    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_25_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
    ieri
    0.38
    قرار
    0.38
    箅
    0.36
    فيق
    0.36
    炙
    0.36
    ಕ್ಕ
    0.35
    elsey
    0.35
    üssel
    0.35
    னே
    0.34
     엄청
    0.34
    POSITIVE LOGITS
     misunderstood
    0.38
     reviving
    0.35
     protégé
    0.34
     erud
    0.34
     clips
    0.33
     கண்டு
    0.33
    の人気
    0.32
     ನಡೆ
    0.32
     ታ
    0.32
    тацию
    0.32
    Activations Density 0.001%

    No Known Activations