© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62637
    Prev
    Next
    INDEX
    Explanations

    c stdio functions

    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_41_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
    peza
    0.39
     Hyun
    0.37
     vj
    0.37
    ើញ
    0.37
    Hình
    0.36
    गुज
    0.36
     đảo
    0.36
     問
    0.36
     ""}
    0.36
    Hiện
    0.36
    POSITIVE LOGITS
     ln
    0.66
    ln
    0.61
    ongoose
    0.46
    θο
    0.44
     LN
    0.43
    sprintf
    0.42
    Spr
    0.40
    lnk
    0.40
    FP
    0.40
    sstream
    0.40
    Activations Density 0.001%

    No Known Activations