© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41190
    Prev
    Next
    INDEX
    Explanations

    return None

    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_22_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
     geopol
    0.49
     episcopal
    0.46
     prose
    0.41
     downward
    0.41
    ્રી
    0.41
     brev
    0.41
     pronunciation
    0.41
     embora
    0.39
    ė
    0.39
     pron
    0.39
    POSITIVE LOGITS
    wise
    0.40
    FIED
    0.38
    と呼ばれる
    0.36
     หรือ
    0.35
    SOL
    0.35
     혹은
    0.35
     struck
    0.35
    悉
    0.35
    onato
    0.35
    asionally
    0.35
    Activations Density 0.006%

    No Known Activations