© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50557
    Prev
    Next
    INDEX
    Explanations

    how led

    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_10_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
    이지만
    0.51
    برا
    0.50
    و
    0.50
    ين
    0.49
    이면
    0.47
    尴
    0.47
    畞
    0.47
    Danh
    0.46
    이었
    0.46
    Inode
    0.46
    POSITIVE LOGITS
    3
    0.55
     n
    0.54
     ,
    0.52
    1
    0.50
    .,
    0.49
    *,
    0.49
    ’
    0.47
    ί
    0.46
     r
    0.46
     ₹
    0.46
    Activations Density 0.009%

    No Known Activations