© 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. 198621
    Prev
    Next
    INDEX
    Explanations

    ** appendix

    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
    草
    0.48
    唤
    0.46
    že
    0.46
    ision
    0.45
    这是
    0.45
    干燥
    0.45
    別
    0.45
    莲
    0.45
    mari
    0.45
    يمكن
    0.44
    POSITIVE LOGITS
     된다
    0.54
     тебе
    0.52
     เงี้ย
    0.50
     cunt
    0.49
     Expt
    0.48
     неу
    0.48
     குதிக
    0.47
     оце
    0.46
     появи
    0.46
     дают
    0.46
    Activations Density 0.000%

    No Known Activations