© 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. 36736
    Prev
    Next
    INDEX
    Explanations

    create, mkdir, initialize

    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
    Not in Any Lists

    No Comments

    Negative Logits
     վ
    0.41
     ওঠার
    0.38
    墓志
    0.37
    逋
    0.37
     représenter
    0.37
     नाइट्रोजन
    0.37
     Petron
    0.36
     वाहन
    0.36
    減
    0.36
     пробе
    0.35
    POSITIVE LOGITS
    Created
    0.46
     created
    0.43
     initialize
    0.41
     initializing
    0.41
     initializes
    0.41
     create
    0.40
     erstellen
    0.39
    zca
    0.39
    enche
    0.38
     creation
    0.38
    Activations Density 0.101%

    No Known Activations