© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76706
    Prev
    Next
    INDEX
    Explanations

    script import statements

    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
    Die
    0.33
     Nee
    0.33
     வயிற்றில்
    0.30
     sorriso
    0.30
    commercial
    0.29
    ക്ഷി
    0.29
    緩
    0.29
    مرار
    0.28
    ֹ
    0.28
    تبار
    0.27
    POSITIVE LOGITS
     thorough
    0.34
     méxico
    0.34
     whol
    0.32
     joystick
    0.32
     penalty
    0.31
     maximum
    0.31
     maxima
    0.31
     quantas
    0.30
     maximale
    0.30
     muff
    0.30
    Activations Density 0.000%

    No Known Activations