© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220991
    Prev
    Next
    INDEX
    Explanations

    minimal effort

    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_10_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
    3
    0.87
    7
    0.79
     casa
    0.77
    博客
    0.75
     Много
    0.74
    נס
    0.73
    見える
    0.72
    ﻪ
    0.72
     pasada
    0.71
     Vodafone
    0.71
    POSITIVE LOGITS
    on
    1.25
    ol
    1.10
    us
    1.09
    it
    1.09
    urized
    1.00
    ar
    0.96
    onin
    0.93
    uhe
    0.93
    ad
    0.91
    ai
    0.91
    Activations Density 0.005%

    No Known Activations