© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35951
    Prev
    Next
    INDEX
    Explanations

    T-Rex bite force

    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
    出
    0.76
     концов
    0.72
    un
    0.69
    förm
    0.66
    f
    0.64
    filled
    0.63
    fed
    0.62
    therapeutic
    0.62
     infrequent
    0.61
    nThe
    0.61
    POSITIVE LOGITS
    (),
    0.96
    ри
    0.77
    شي
    0.75
    ט
    0.70
    ల
    0.67
    ла
    0.66
    લ
    0.65
    wl
    0.64
    ні
    0.64
    ونية
    0.63
    Activations Density 0.002%

    No Known Activations