© 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. 215609
    Prev
    Next
    INDEX
    Explanations

    terms and conditions agreed

    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
     vocab
    0.40
    Finish
    0.37
    剥
    0.36
     utas
    0.35
    缄
    0.34
    HttpContext
    0.34
    ிலோ
    0.34
    break
    0.33
    ート
    0.33
    សំណ
    0.33
    POSITIVE LOGITS
    eku
    0.35
     முதுகு
    0.34
    บา
    0.34
     esperti
    0.32
    оти
    0.32
     odborn
    0.32
     Zy
    0.31
    団
    0.31
     Rahman
    0.31
     بل
    0.31
    Activations Density 0.000%

    No Known Activations