© 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. 31939
    Prev
    Next
    INDEX
    Explanations

    . (followed by args, Script, Message)

    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
     sensibly
    0.38
     മൈ
    0.36
    CONTENTS
    0.35
     chú
    0.34
    γγελ
    0.34
    ሜ
    0.34
     तलैया
    0.34
    とされる
    0.33
    Cpu
    0.33
    Celeron
    0.33
    POSITIVE LOGITS
    ittura
    0.39
    hette
    0.38
    ляр
    0.38
    ज़ा
    0.36
    합
    0.36
     Ve
    0.35
     Munch
    0.34
    Won
    0.34
     পুত্রের
    0.34
    㑼
    0.34
    Activations Density 0.010%

    No Known Activations