© 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. 125634
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    t
    1.06
    ت
    0.86
    and
    0.85
    x
    0.73
    ed
    0.72
    al
    0.71
    tio
    0.69
    ing
    0.68
    us
    0.67
    en
    0.66
    POSITIVE LOGITS
    کام
    0.72
    ！？
    0.69
    ク
    0.68
    م
    0.68
    ін
    0.68
    ナ
    0.68
    м
    0.67
    נ
    0.67
    イ
    0.66
    される
    0.66
    Activations Density 0.000%

    No Known Activations