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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62780
    Prev
    Next
    INDEX
    Explanations

    of type, kind, sort

    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_41_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
     ठे
    0.36
     व्यवस्थित
    0.36
     Tender
    0.36
     cellules
    0.34
    櫸
    0.34
     tenderness
    0.33
     Dhan
    0.33
     সমঝো
    0.33
    𒁍
    0.33
    ಮಿ
    0.33
    POSITIVE LOGITS
     sort
    1.96
     kind
    1.74
    sort
    1.57
     sorts
    1.57
     sorta
    1.52
    Sort
    1.46
     Sort
    1.44
     kinda
    1.41
     soort
    1.38
    kind
    1.35
    Activations Density 0.027%

    No Known Activations