© 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. 214914
    Prev
    Next
    INDEX
    Explanations

    adding to collections

    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
     educating
    0.41
     join
    0.41
     educate
    0.41
     Educ
    0.39
     tier
    0.38
    ностях
    0.38
     cite
    0.37
    Ϥ
    0.35
    hlt
    0.35
    鮋
    0.34
    POSITIVE LOGITS
    口袋
    0.38
    Holding
    0.37
     சரிய
    0.35
    ION
    0.35
    pués
    0.34
    一只
    0.34
     동작
    0.34
    urable
    0.33
    REAL
    0.33
     대부분
    0.33
    Activations Density 0.002%

    No Known Activations