© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35734
    Prev
    Next
    INDEX
    Explanations

    file paths and programming components

    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_11_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
    荃
    0.44
     Lieben
    0.40
    is
    0.40
     lành
    0.39
    时间
    0.38
     Wilmington
    0.38
    ल
    0.38
    isesti
    0.38
     позволя
    0.38
    权限
    0.37
    POSITIVE LOGITS
     oni
    0.41
     to
    0.41
    t
    0.41
     that
    0.40
     who
    0.38
    ﺎ
    0.36
     octubre
    0.35
    ாவ
    0.35
     augment
    0.35
     OS
    0.34
    Activations Density 0.005%

    No Known Activations