© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42573
    Prev
    Next
    INDEX
    Explanations

    Bugatti or Bentley models

    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_13_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
    л
    0.68
     часть
    0.60
     t
    0.59
    ल
    0.56
     т
    0.55
    ತ್ನ
    0.54
    цаў
    0.54
     Турции
    0.54
    энд
    0.52
    𝓈
    0.52
    POSITIVE LOGITS
    up
    0.50
    fen
    0.46
     Kleine
    0.46
    www
    0.45
    filename
    0.45
    lets
    0.44
    phoneNumber
    0.44
    ola
    0.44
    irm
    0.43
    za
    0.43
    Activations Density 0.000%

    No Known Activations