© 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. 34494
    Prev
    Next
    INDEX
    Explanations

    full-stack developer or full-fat ingredients

    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
    لي
    0.79
    nější
    0.70
    ني
    0.63
    在
    0.61
     في
    0.61
     toán
    0.60
     رئيس
    0.60
    <0x91>
    0.59
    cccnc
    0.59
    碜
    0.58
    POSITIVE LOGITS
    ar
    0.81
    ו
    0.80
    in
    0.80
    I
    0.77
    o
    0.75
    ung
    0.73
    u
    0.73
    et
    0.73
    のは
    0.72
    er
    0.71
    Activations Density 0.012%

    No Known Activations