© 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. 242700
    Prev
    Next
    INDEX
    Explanations

    list item

    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
    ەن
    0.43
     밝
    0.41
     밝혔
    0.39
    enas
    0.39
    bright
    0.39
    盎
    0.38
     punct
    0.38
    crates
    0.38
    밝
    0.37
    keye
    0.36
    POSITIVE LOGITS
     comprendre
    0.45
     toprak
    0.41
     Gén
    0.40
    READ
    0.40
    開発
    0.39
     développement
    0.39
     Development
    0.38
     новой
    0.38
     nouvelle
    0.38
    Development
    0.38
    Activations Density 0.010%

    No Known Activations