© 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. 127420
    Prev
    Next
    INDEX
    Explanations

    quarter horse combat

    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
    み
    0.75
    k
    0.72
     Princip
    0.64
    жи
    0.63
    鼕
    0.63
    ່າ
    0.62
    用
    0.61
    getSaveLocation
    0.61
    körper
    0.60
    بدا
    0.59
    POSITIVE LOGITS
     to
    1.13
    Quarter
    1.01
     quarter
    0.92
     by
    0.87
     Quarter
    0.87
     not
    0.87
    ן
    0.83
     r
    0.83
    I
    0.81
     as
    0.79
    Activations Density 0.001%

    No Known Activations