© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246102
    Prev
    Next
    INDEX
    Explanations

    automation programming

    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_40_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
    প্ট
    0.36
     matching
    0.36
    ાવી
    0.36
    Otro
    0.35
    otro
    0.34
     mirror
    0.34
    ('.')[
    0.33
    收取
    0.33
     Series
    0.33
    konto
    0.32
    POSITIVE LOGITS
     রাশ
    0.37
    ester
    0.37
    汤
    0.37
     testamentary
    0.36
    字节
    0.36
    RUP
    0.36
     définit
    0.36
     resett
    0.36
    গ্রামে
    0.35
    насти
    0.35
    Activations Density 0.001%

    No Known Activations