© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148463
    Prev
    Next
    INDEX
    Explanations

    dream recounting

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     rans
    0.46
     Universal
    0.46
     star
    0.41
     Base
    0.38
    Universal
    0.38
     gamble
    0.37
    رمین
    0.37
    ᱠ
    0.37
     bunker
    0.37
     ইন্ডাস্ট্র
    0.37
    POSITIVE LOGITS
    ół
    0.47
     реконструк
    0.44
    suites
    0.43
     этом
    0.42
    ــــــــ
    0.39
    ෞ
    0.39
    getRedTeam
    0.39
     세포
    0.38
     следующий
    0.37
     願い
    0.37
    Activations Density 0.002%

    No Known Activations