© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98883
    Prev
    Next
    INDEX
    Explanations

    fault isolation

    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_16_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
    :
    0.64
    usive
    0.58
    utch
    0.53
    ute
    0.49
    ír
    0.48
    uren
    0.46
    üt
    0.45
     '
    0.43
    ured
    0.43
    ocaly
    0.43
    POSITIVE LOGITS
     ಅರ್ಜಿ
    0.61
     бонусы
    0.54
     ingeniería
    0.53
     tasarım
    0.53
     NEED
    0.53
     ব্যবসার
    0.53
     trabalhar
    0.52
     bawang
    0.52
     distribuzione
    0.51
     trabaja
    0.50
    Activations Density 0.000%

    No Known Activations