© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38620
    Prev
    Next
    INDEX
    Explanations

    when we

    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_3_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
    s
    0.76
    kannya
    0.68
     була
    0.63
    sby
    0.61
    Ку
    0.58
    saan
    0.55
    was
    0.55
     normality
    0.54
     dispon
    0.53
     lessor
    0.53
    POSITIVE LOGITS
    ó
    0.88
    ih
    0.82
    f
    0.80
    $\$
    0.73
    IM
    0.72
     año
    0.72
    ā
    0.71
    ol
    0.70
    ੁ
    0.70
    é
    0.68
    Activations Density 0.002%

    No Known Activations