© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11737
    Prev
    Next
    INDEX
    Explanations

    variable names in code

    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_13_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
    ING
    0.24
    Submit
    0.22
    .*
    0.22
     تک
    0.21
     கரைச
    0.21
    Pentru
    0.21
     egip
    0.21
    ummy
    0.21
    ¹.
    0.21
    aryng
    0.20
    POSITIVE LOGITS
    랐
    0.19
    нг
    0.18
     Länder
    0.18
     Staaten
    0.17
     voet
    0.17
     Tomás
    0.17
    షన్
    0.17
     Ра
    0.17
     director
    0.16
     Psychological
    0.16
    Activations Density 0.003%

    No Known Activations