© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126115
    Prev
    Next
    INDEX
    Explanations

    important note/caveat introduction

    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_37_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
     magnes
    0.38
     mags
    0.37
     -&
    0.36
    DP
    0.36
     постоянно
    0.36
     निगाह
    0.36
     Rocky
    0.36
    ISupport
    0.36
     ironically
    0.35
     Scient
    0.35
    POSITIVE LOGITS
    拼
    0.42
     diagnostic
    0.40
     reassurance
    0.38
    slideDuplicate
    0.38
     阿
    0.37
    flickr
    0.37
     wymag
    0.35
     punctuation
    0.34
    كمان
    0.34
    ipun
    0.34
    Activations Density 0.012%

    No Known Activations