© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80728
    Prev
    Next
    INDEX
    Explanations

    coordinates, indices, or number ranges

    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_31_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
    truths
    0.39
    RTC
    0.37
    佯
    0.36
    ックレス
    0.36
    Nope
    0.35
    Respond
    0.35
     RTC
    0.34
    ىن
    0.33
    ოვნ
    0.33
    gig
    0.33
    POSITIVE LOGITS
     표
    0.44
     По
    0.37
     table
    0.37
     perché
    0.37
     Porque
    0.37
     Parsing
    0.35
     deve
    0.35
     dinheiro
    0.35
    เพราะ
    0.35
     porque
    0.34
    Activations Density 0.002%

    No Known Activations