© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181262
    Prev
    Next
    INDEX
    Explanations

    copies

    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_24_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
    subfloat
    0.38
    ‾
    0.37
    探讨
    0.36
    γε
    0.36
    了
    0.35
     Sylvie
    0.34
     conveyors
    0.34
     lounges
    0.34
     requested
    0.34
     horizons
    0.34
    POSITIVE LOGITS
    amous
    0.41
    pp
    0.41
    hesus
    0.39
     huh
    0.39
    wass
    0.39
     trasp
    0.39
    قام
    0.38
    ቫ
    0.38
     думаю
    0.37
    ampoo
    0.37
    Activations Density 0.001%

    No Known Activations