© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249105
    Prev
    Next
    INDEX
    Explanations

    say "s"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     알아
    0.38
    blockList
    0.36
    ServiceObject
    0.36
    ğan
    0.36
    खंड
    0.34
    aborasi
    0.34
     안내
    0.34
     २
    0.34
    递
    0.34
    माग
    0.33
    POSITIVE LOGITS
     s
    2.34
     с
    1.93
     س
    1.78
     स
    1.72
     স
    1.34
     સ
    1.22
     ס
    1.02
    ส
    0.95
     ச
    0.94
     స
    0.92
    Activations Density 0.011%

    No Known Activations