© 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. 28262
    Prev
    Next
    INDEX
    Explanations

    -

    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
    option
    0.42
    nog
    0.39
    drv
    0.37
     বক্তব্যে
    0.35
     read
    0.35
     unes
    0.35
    ᄌ
    0.34
     old
    0.34
    rude
    0.34
    Dre
    0.34
    POSITIVE LOGITS
     বসিয়
    0.38
     अपरा
    0.38
     अधीनस्थ
    0.38
     llegada
    0.38
     diseñada
    0.36
     Während
    0.36
     molestias
    0.36
    㑨
    0.36
     चु
    0.35
     লুকিয়ে
    0.35
    Activations Density 0.010%

    No Known Activations