© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8844
    Prev
    Next
    INDEX
    Explanations

    combine ingredients

    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_13_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
    َب
    0.55
    ADAS
    0.52
     mieszkańców
    0.50
     예약
    0.50
    驾驶
    0.49
    =",
    0.48
    🄴
    0.47
     możliwość
    0.47
     unreasonably
    0.46
    REE
    0.46
    POSITIVE LOGITS
    äm
    0.52
    udging
    0.50
    ommen
    0.49
    om
    0.48
    ফাই
    0.47
    G
    0.47
     he
    0.46
    ming
    0.46
     affective
    0.46
     huruf
    0.45
    Activations Density 0.052%

    No Known Activations