© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199901
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     every
    0.41
    every
    0.41
     kila
    0.39
     perfettamente
    0.39
     всеки
    0.39
     perfectly
    0.38
     setiap
    0.38
    ڵ
    0.38
     Every
    0.38
    ben
    0.37
    POSITIVE LOGITS
     bundle
    0.39
     vouchers
    0.38
     হা
    0.37
     bagels
    0.37
     এভাবে
    0.37
     Mujeres
    0.37
     acres
    0.36
     rè
    0.36
     affinities
    0.36
     bundles
    0.36
    Activations Density 0.016%

    No Known Activations