© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7160
    Prev
    Next
    INDEX
    Explanations

    musical notation

    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_40_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
    oint
    0.42
     xii
    0.40
    페이지
    0.40
    礦
    0.38
    harvard
    0.38
    ຫຼ
    0.37
     শিশ
    0.37
    Theta
    0.36
    zyć
    0.36
    nel
    0.35
    POSITIVE LOGITS
     Champion
    0.46
     чемпионаты
    0.44
    Champion
    0.44
    agat
    0.43
    Entered
    0.43
     Entered
    0.43
     чемпион
    0.43
     чемпи
    0.41
     (#
    0.41
     champion
    0.40
    Activations Density 0.028%

    No Known Activations