© 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. 23971
    Prev
    Next
    INDEX
    Explanations

    greatest number

    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
     ବ
    0.35
     بہت
    0.32
    ”،
    0.32
     Раз
    0.32
     হেতু
    0.30
    ógico
    0.30
     ប៉ុ
    0.30
     Chí
    0.30
     IncludeField
    0.30
     कैलकु
    0.30
    POSITIVE LOGITS
     your
    0.36
     some
    0.34
     :'
    0.33
     its
    0.32
    :[
    0.31
     thy
    0.30
     yours
    0.30
    :$
    0.30
    ::
    0.30
    some
    0.29
    Activations Density 0.012%

    No Known Activations