© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194207
    Prev
    Next
    INDEX
    Explanations

    NIV translation

    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_9_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
    ле
    0.85
    نی
    0.75
    ↵↵
    0.74
    is
    0.74
    них
    0.73
    us
    0.70
    最
    0.68
    ifts
    0.68
    ન
    0.68
    و
    0.67
    POSITIVE LOGITS
     be
    0.88
     pruebas
    0.75
     guia
    0.75
     کل
    0.73
     árboles
    0.73
     mêmes
    0.73
     derece
    0.73
     plantations
    0.72
    cribable
    0.71
     lié
    0.71
    Activations Density 0.000%

    No Known Activations