© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208996
    Prev
    Next
    INDEX
    Explanations

    numeric list items

    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_25_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
    ्य
    0.40
    ildir
    0.39
    luents
    0.38
    હુ
    0.38
    ͞
    0.38
     نحل
    0.37
    şık
    0.37
    ́
    0.37
     प्रतिभा
    0.36
     ஏராளமான
    0.36
    POSITIVE LOGITS
     leveling
    0.42
     pourcentage
    0.42
     pointers
    0.40
     profit
    0.39
     adrenalin
    0.39
     flashbacks
    0.39
     coupons
    0.38
     achar
    0.38
     recommand
    0.38
     nuggets
    0.37
    Activations Density 0.001%

    No Known Activations