© 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. 46802
    Prev
    Next
    INDEX
    Explanations

    cracking knuckles

    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
    )]
    0.59
    ı
    0.57
    ة
    0.57
    3
    0.56
    ion
    0.55
     difíciles
    0.54
    መሪያ
    0.52
    ложение
    0.52
    ifères
    0.52
    mathbf
    0.50
    POSITIVE LOGITS
    s
    0.65
    स
    0.63
    '
    0.60
    지
    0.53
    a
    0.50
    0.48
    y
    0.47
     de
    0.47
     to
    0.46
     sugger
    0.46
    Activations Density 0.001%

    No Known Activations