© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199125
    Prev
    Next
    INDEX
    Explanations

    AAD, ES, Stat, Etsy

    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_15_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
     box
    0.48
     defiance
    0.48
     oblivion
    0.47
     m
    0.46
    ব
    0.46
     behavioral
    0.45
     mange
    0.45
     brute
    0.44
     avian
    0.44
     prob
    0.44
    POSITIVE LOGITS
     தோட்டங்கள்
    0.63
    ла
    0.56
     एक्ट्रेसेस
    0.56
     क्लोरीन
    0.55
    6
    0.54
     চার্জ
    0.53
    ])$.
    0.53
    classteacher
    0.52
    ']
    0.52
    事项
    0.52
    Activations Density 0.000%

    No Known Activations