© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18153
    Prev
    Next
    INDEX
    Explanations

    reviewReviewsreviews

    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_15_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
    :$
    0.41
     ત્રણ
    0.40
    마
    0.38
    :
    0.38
    MENTS
    0.37
    ：
    0.37
     때
    0.37
    yal
    0.36
    때
    0.36
    估计
    0.36
    POSITIVE LOGITS
     Ин
    0.40
     Protector
    0.40
     Бога
    0.39
     Española
    0.39
    सेच
    0.39
     офи
    0.38
     ousted
    0.38
     ø
    0.38
     हृ
    0.38
     জগতের
    0.38
    Activations Density 0.013%

    No Known Activations