© 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. 46353
    Prev
    Next
    INDEX
    Explanations

    after 'as'

    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
    酘
    0.44
    лее
    0.43
    сера
    0.42
    zonego
    0.41
    Lives
    0.38
     دیکھیں
    0.38
     formulaire
    0.38
     صورت
    0.37
    jectory
    0.37
    стера
    0.37
    POSITIVE LOGITS
     camps
    0.46
     thus
    0.44
    🥐
    0.44
     force
    0.42
     landings
    0.41
    nais
    0.41
     así
    0.41
     possession
    0.41
     asset
    0.41
     cafes
    0.41
    Activations Density 0.000%

    No Known Activations