© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104853
    Prev
    Next
    INDEX
    Explanations

    articles, pronouns, and 'no'

    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_1_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
    。
    0.77
    '`--
    0.73
    ה
    0.71
    ㈣
    0.70
    kannya
    0.69
    みて
    0.68
     รวมถึง
    0.66
    ा
    0.65
     ภาพ
    0.63
     furtherance
    0.63
    POSITIVE LOGITS
    s
    1.23
     for
    1.06
    та
    0.99
    is
    0.98
    ص
    0.98
    ad
    0.97
     can
    0.96
    ু
    0.92
    can
    0.91
    Content
    0.91
    Activations Density 0.001%

    No Known Activations