© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205549
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    э
    0.47
     Wash
    0.43
    ণ্ড
    0.41
    isier
    0.41
    Ђ
    0.40
    Э
    0.40
    Ց
    0.39
     ७
    0.38
     งาน
    0.38
    эк
    0.38
    POSITIVE LOGITS
    <unused44>
    0.41
    <end_of_turn>
    0.39
     terutama
    0.38
    ោយ
    0.37
    юць
    0.35
    หลัก
    0.34
    エース
    0.34
    觚
    0.34
    ไ
    0.34
     sag
    0.33
    Activations Density 0.043%

    No Known Activations