© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18425
    Prev
    Next
    INDEX
    Explanations

    linspace

    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_15_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
    ้
    0.49
     helix
    0.48
     multi
    0.47
    器
    0.47
     bootstra
    0.47
    ุม
    0.47
     multist
    0.47
     symphony
    0.46
     micro
    0.46
    Reader
    0.46
    POSITIVE LOGITS
    regelen
    0.61
     Position
    0.59
    туа
    0.58
     sektor
    0.57
    onesian
    0.57
     %.
    0.56
     Guilherme
    0.56
    pev
    0.56
     čet
    0.55
     Sector
    0.55
    Activations Density 0.003%

    No Known Activations