© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121033
    Prev
    Next
    INDEX
    Explanations

    `__init__`

    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_37_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
     sweats
    0.40
    zilla
    0.37
     hardworking
    0.37
     gun
    0.37
     servers
    0.36
    RELATIVA
    0.35
    orpio
    0.35
    DebugInformation
    0.35
     metals
    0.34
    铳
    0.34
    POSITIVE LOGITS
    initialize
    0.61
    init
    0.57
    initial
    0.56
    INIT
    0.56
     initialize
    0.55
     Initialize
    0.53
    initialized
    0.52
    初始化
    0.51
    initializer
    0.51
     init
    0.50
    Activations Density 0.000%

    No Known Activations