© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126713
    Prev
    Next
    INDEX
    Explanations

    request parameters

    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_37_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
     पात्र
    0.44
    ᱞ
    0.40
     পাত্র
    0.39
     createContext
    0.39
     mediators
    0.39
     modalities
    0.38
     ইয়
    0.38
     يول
    0.38
    煞
    0.37
     markets
    0.37
    POSITIVE LOGITS
    ký
    0.43
    esterly
    0.38
    kého
    0.37
    цэ
    0.37
    زيز
    0.36
    Killer
    0.35
    ᆢ
    0.35
     Dwight
    0.34
    viat
    0.34
    ERV
    0.34
    Activations Density 0.001%

    No Known Activations