© 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. 195168
    Prev
    Next
    INDEX
    Explanations

    location names and descriptions

    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
     benefiting
    0.54
     benefitting
    0.52
    formance
    0.51
     áreas
    0.50
    ≋
    0.49
    ◾
    0.48
    ?>"
    0.47
     servicio
    0.47
    ⌯
    0.47
     आत्मविश्वास
    0.47
    POSITIVE LOGITS
     сказал
    0.56
     שא
    0.50
     писа
    0.49
    談
    0.49
     занимается
    0.49
     را
    0.47
     شركات
    0.47
    公司的
    0.46
     ม
    0.46
     disagrees
    0.46
    Activations Density 0.000%

    No Known Activations