© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47495
    Prev
    Next
    INDEX
    Explanations

    strength

    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_10_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
    ។
    0.29
    র
    0.28
     Հ
    0.27
    ર
    0.27
    ные
    0.27
     Ее
    0.27
     MoU
    0.26
    serverResponse
    0.26
     Боли
    0.26
    ра
    0.26
    POSITIVE LOGITS
    ’
    0.43
    '
    0.30
     използ
    0.26
     форме
    0.25
     attaqu
    0.24
    Methods
    0.24
    County
    0.24
     évalu
    0.23
     problème
    0.23
     at
    0.23
    Activations Density 0.018%

    No Known Activations