© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81270
    Prev
    Next
    INDEX
    Explanations

    entity IDs and codes

    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_31_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
     auquel
    0.33
     जाधव
    0.31
    bleeds
    0.30
     hesitation
    0.29
     ದೂರ
    0.28
    bleed
    0.28
     کوشش
    0.28
     ईद
    0.28
    berge
    0.28
    物
    0.28
    POSITIVE LOGITS
     eril
    0.35
     criaturas
    0.35
     tecnici
    0.34
    ductor
    0.32
    angerschaft
    0.32
    untes
    0.32
     telas
    0.32
     réun
    0.30
    firestore
    0.30
     tecnologias
    0.30
    Activations Density 0.005%

    No Known Activations