© 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. 23399
    Prev
    Next
    INDEX
    Explanations

    displays

    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
     isother
    0.40
    खन
    0.37
    洗濯
    0.37
    charm
    0.36
    कुर
    0.36
    रहे
    0.36
    اين
    0.35
    詛
    0.35
     Kur
    0.34
     दिल
    0.34
    POSITIVE LOGITS
     displays
    1.41
     display
    1.38
    display
    1.27
     Displays
    1.27
    Displays
    1.22
    displays
    1.20
     displaying
    1.16
    Display
    1.13
     Display
    1.13
     DISPLAYS
    1.13
    Activations Density 0.006%

    No Known Activations