© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14382
    Prev
    Next
    INDEX
    Explanations

    Optim or Optimism

    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_15_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
     З
    0.56
     Z
    0.55
     Yok
    0.53
     JI
    0.53
     ys
    0.52
     الملف
    0.52
     Ý
    0.52
     තු
    0.51
     BSData
    0.51
     td
    0.50
    POSITIVE LOGITS
    Vin
    0.61
    estine
    0.57
    year
    0.55
    Contact
    0.55
    Burning
    0.55
    Código
    0.55
    Complement
    0.55
    年
    0.54
    ínio
    0.54
    Clique
    0.54
    Activations Density 0.003%

    No Known Activations