© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36782
    Prev
    Next
    INDEX
    Explanations

    have to/a

    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_11_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
     হাসপাত
    0.71
    ର୍
    0.64
     Хотя
    0.64
     Conseils
    0.63
    𝗛
    0.61
    వృద్ధి
    0.59
    ћин
    0.57
    👶
    0.57
    Ꮮ
    0.57
    𝗥
    0.56
    POSITIVE LOGITS
     president
    0.60
     cheaper
    0.60
     place
    0.60
     two
    0.59
     state
    0.58
     NG
    0.57
     do
    0.57
     first
    0.57
     "
    0.57
     ATV
    0.57
    Activations Density 0.002%

    No Known Activations