© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216297
    Prev
    Next
    INDEX
    Explanations

    chapter divisions and numbers

    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_31_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
    embedded
    0.39
    Ὅ
    0.39
    叻
    0.38
    知道了
    0.38
    Picking
    0.38
     પ્રાપ્ત
    0.37
     receita
    0.36
     έχουν
    0.36
    Sticky
    0.36
     Abstand
    0.35
    POSITIVE LOGITS
    iskup
    0.37
     設計
    0.37
     QtCore
    0.35
    設計
    0.35
    斕
    0.34
     càng
    0.34
     [$
    0.34
    arendon
    0.33
     қара
    0.33
    ostrum
    0.33
    Activations Density 0.000%

    No Known Activations