© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142884
    Prev
    Next
    INDEX
    Explanations

    overblown or windblown

    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_0_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
    I
    1.38
    0
    1.33
    ０
    1.26
     αλλά
    1.25
    ۰
    1.23
     αυτό
    1.23
     elucid
    1.18
    ๐
    1.06
    
    1.06
     admissible
    1.05
    POSITIVE LOGITS
    ש
    1.62
    д
    1.59
    is
    1.52
    ت
    1.41
    ز
    1.39
    كان
    1.38
     a
    1.28
    on
    1.25
    يل
    1.23
    ч
    1.22
    Activations Density 0.000%

    No Known Activations