© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15522
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English words

    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_34_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
    LAN
    0.37
     ++;
    0.37
     ",",
    0.34
    ड़क
    0.34
     .,
    0.33
     **,
    0.33
    ľov
    0.33
    गरण
    0.32
    Essex
    0.32
    saldo
    0.32
    POSITIVE LOGITS
    ácio
    0.36
    хва
    0.36
    vants
    0.35
     dec
    0.35
    ાવ
    0.35
     proteger
    0.35
    ercus
    0.35
    ɣ
    0.34
     बाज
    0.33
    FromName
    0.33
    Activations Density 0.000%

    No Known Activations