© 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. 76148
    Prev
    Next
    INDEX
    Explanations

    anything specific or else

    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
     steadily
    0.35
    딛
    0.34
     ক্লাব
    0.34
     Question
    0.33
    ड़ी
    0.33
     rooted
    0.33
     brewed
    0.33
     Orchestra
    0.33
     oblige
    0.33
    鶯
    0.32
    POSITIVE LOGITS
    Equal
    0.38
    Defaults
    0.38
    ignes
    0.37
    Missing
    0.37
     પેટ
    0.36
    缺失
    0.36
     fehl
    0.36
    Stat
    0.36
    Greater
    0.36
    Adjacent
    0.36
    Activations Density 0.001%

    No Known Activations