© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201482
    Prev
    Next
    INDEX
    Explanations

    authentication library

    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_12_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
    alloween
    0.36
    Health
    0.32
    lebih
    0.32
    ➩
    0.32
    送料無料
    0.31
    ILABLE
    0.31
    IRONMENT
    0.31
    ✿
    0.30
    ▦
    0.30
    Stylesheet
    0.30
    POSITIVE LOGITS
     Ger
    0.33
    يد
    0.31
     dels
    0.29
    таж
    0.29
    iz
    0.29
     building
    0.29
     end
    0.28
     Game
    0.28
     Apple
    0.28
     director
    0.28
    Activations Density 0.001%

    No Known Activations