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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15859
    Prev
    Next
    INDEX
    Explanations

    back to state

    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_34_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
     Integral
    0.39
     মাসুদ
    0.37
     Boliv
    0.36
     integral
    0.35
     Attend
    0.35
     integrale
    0.35
    寜
    0.35
     conception
    0.35
    Integral
    0.35
     jūn
    0.35
    POSITIVE LOGITS
    状態
    0.54
     состояния
    0.52
    陷
    0.52
     состоянии
    0.51
     حالت
    0.51
    保持
    0.50
    State
    0.50
     상태
    0.49
    状态
    0.48
    getState
    0.48
    Activations Density 0.112%

    No Known Activations