© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48510
    Prev
    Next
    INDEX
    Explanations

    hornUsed Method 1 because MAX_ACTIVATING_TOKENS are all variations of "horn"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    Best
    0.42
    的最佳
    0.42
     Best
    0.41
     बेस्ट
    0.40
     best
    0.38
    best
    0.38
     keySchedule
    0.36
    ゥ
    0.36
    的其他
    0.35
    㞓
    0.35
    POSITIVE LOGITS
    อร์ด
    0.38
    ugin
    0.37
    広い
    0.37
    されない
    0.36
    ಟ್
    0.34
    ദ്യ
    0.34
    ulton
    0.34
    ેલા
    0.34
    لیفون
    0.34
    elton
    0.33
    Activations Density 0.000%

    No Known Activations