© 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. 205799
    Prev
    Next
    INDEX
    Explanations

    door or window frames

    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
    Not in Any Lists

    No Comments

    Negative Logits
    VERSE
    0.45
     نوع
    0.45
     Wynne
    0.45
     定义
    0.42
    驛
    0.41
     type
    0.40
    نوع
    0.40
     traitements
    0.40
     NÃO
    0.39
     Mädchen
    0.39
    POSITIVE LOGITS
    ut
    0.52
    on
    0.48
     Букмекердик
    0.45
     iv
    0.45
    j
    0.44
     bundle
    0.44
    exist
    0.44
    item
    0.44
    സ്തു
    0.44
    ge
    0.43
    Activations Density 0.000%

    No Known Activations