© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86042
    Prev
    Next
    INDEX
    Explanations

    Simpson, Kiyosaki, Kiesselbach, Kiyomi

    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_3_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
    '
    1.02
    ri
    0.85
    هم
    0.84
    it
    0.80
    ص
    0.76
     of
    0.74
    mma
    0.71
    របស់
    0.71
    ters
    0.68
    Lie
    0.68
    POSITIVE LOGITS
    一流
    0.79
    ко
    0.67
    嶈
    0.67
    ాడు
    0.66
    ид
    0.66
    ﻧ
    0.66
    𝐞
    0.64
    ﯾ
    0.64
    一笑
    0.64
    в
    0.63
    Activations Density 0.009%

    No Known Activations