© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204833
    Prev
    Next
    INDEX
    Explanations

    eccentric

    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_56_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
     एक्सरसा
    0.39
    
    0.38
     stat
    0.38
    괵
    0.38
    edown
    0.37
     commenc
    0.37
    }={
    0.37
     freg
    0.36
     nouve
    0.35
    mogorov
    0.35
    POSITIVE LOGITS
    iciaire
    0.38
     robustness
    0.37
    術
    0.37
    umes
    0.35
    tir
    0.35
    ベージュ
    0.35
    imize
    0.34
    налу
    0.34
     натура
    0.34
    يك
    0.33
    Activations Density 0.000%

    No Known Activations