© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86683
    Prev
    Next
    INDEX
    Explanations

    half marathon, Half Dome, Plane

    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_3_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
    ：
    0.74
    ↵
    0.66
    ก
    0.65
     BASF
    0.64
     DFT
    0.63
     SRAM
    0.62
    '
    0.62
    大概
    0.59
    ，
    0.58
    h
    0.58
    POSITIVE LOGITS
     of
    0.77
    ു
    0.74
    এর
    0.72
    র
    0.72
    ્ર
    0.71
    ка
    0.71
     smiles
    0.71
    리
    0.70
    algebras
    0.68
    IT
    0.68
    Activations Density 0.001%

    No Known Activations