© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118410
    Prev
    Next
    INDEX
    Explanations

    ORDER BY clause

    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_27_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
     obey
    0.44
     vaginalis
    0.43
     mechanically
    0.39
    اموش
    0.37
     again
    0.36
     safely
    0.36
    ギ
    0.36
    hemi
    0.36
     rade
    0.35
    您可以
    0.35
    POSITIVE LOGITS
     FaceTime
    0.43
    訖
    0.43
     Booking
    0.40
    නික
    0.38
     മുഖ
    0.38
     সম্মিল
    0.37
    effectuer
    0.36
    丑
    0.36
     Bài
    0.35
    nast
    0.35
    Activations Density 0.001%

    No Known Activations