© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77502
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    ведена
    0.61
    ведении
    0.61
    веден
    0.59
    води
    0.59
     Lead
    0.57
    Lead
    0.57
    ведено
    0.55
    領
    0.54
    领
    0.53
    Led
    0.50
    POSITIVE LOGITS
    ход
    0.48
    ходи
    0.48
    هار
    0.46
    חי
    0.44
    хід
    0.44
    хо
    0.43
    хода
    0.41
    חו
    0.41
    хожу
    0.41
    хождение
    0.39
    Activations Density 0.006%

    No Known Activations