© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79332
    Prev
    Next
    INDEX
    Explanations

    simplicity

    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_0_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
    ي
    1.55
    h
    1.33
    就
    1.30
    是
    1.28
    Y
    1.25
    ।
    1.24
    О
    1.24
    ม
    1.23
    اف
    1.23
    اً
    1.22
    POSITIVE LOGITS
     for
    1.66
     as
    1.16
    та
    1.13
     interne
    1.09
    ia
    1.06
     Salary
    1.06
    getVisibility
    1.05
    уз
    1.04
    ことにより
    1.01
    LookAndFeelInfo
    1.01
    Activations Density 0.001%

    No Known Activations