© 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. 34366
    Prev
    Next
    INDEX
    Explanations

    before, seen, requirement, fetching, photo

    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
    umbling
    0.87
    ح
    0.85
    یه
    0.79
    ė
    0.77
    야
    0.76
    یس
    0.73
    ین
    0.72
    یت
    0.72
    ः
    0.72
    ad
    0.71
    POSITIVE LOGITS
     ممكن
    0.70
    m
    0.68
     mož
    0.66
    ింది
    0.64
     actief
    0.64
    㖮
    0.62
     صحيح
    0.61
    <0xA3>
    0.60
    很多
    0.60
    瑉
    0.60
    Activations Density 0.066%

    No Known Activations