© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148392
    Prev
    Next
    INDEX
    Explanations

    say "from"

    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_59_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
    imageBase
    0.40
    gages
    0.39
     elevationMap
    0.39
    ㍉
    0.38
    atanam
    0.38
    tStart
    0.38
    elective
    0.37
    sPath
    0.37
    (^^
    0.36
    იდან
    0.36
    POSITIVE LOGITS
     van
    0.61
     Van
    0.54
     vannak
    0.49
     von
    0.47
    Van
    0.46
     .
    0.44
     „
    0.44
    ř
    0.44
    on
    0.42
     :
    0.42
    Activations Density 0.001%

    No Known Activations