© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192919
    Prev
    Next
    INDEX
    Explanations

    martial arts

    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_4_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
    it
    1.05
    ت
    0.84
     dukkham
    0.81
    t
    0.81
    seits
    0.79
     marít
    0.79
     estadísticas
    0.79
    iť
    0.78
    이었
    0.77
    나가
    0.75
    POSITIVE LOGITS
     as
    1.64
     is
    1.45
    0
    1.13
     by
    1.10
     on
    1.06
     for
    0.99
    ari
    0.95
     from
    0.95
     has
    0.94
    ash
    0.94
    Activations Density 0.001%

    No Known Activations