© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205542
    Prev
    Next
    INDEX
    Explanations

    local variable declarations

    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_20_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
    そもそも
    0.49
     IAEA
    0.46
     touted
    0.44
    agnetic
    0.44
     Croix
    0.41
     Emory
    0.41
     Saltar
    0.41
     m
    0.41
     Free
    0.41
     Northrop
    0.40
    POSITIVE LOGITS
    ட்சத்திர
    0.43
    λι
    0.42
    тет
    0.42
    ไตล์
    0.41
     rupani
    0.40
    ळून
    0.39
     короля
    0.39
    SPEAK
    0.39
    लियों
    0.39
    ཝ
    0.38
    Activations Density 0.001%

    No Known Activations