© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143773
    Prev
    Next
    INDEX
    Explanations

    engineers associated with professions

    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_0_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
     a
    1.58
    ak
    1.39
    that
    1.28
    ता
    1.22
    ↵↵
    1.18
    S
    1.17
    E
    1.13
    ion
    1.12
    asts
    1.12
    ’
    1.10
    POSITIVE LOGITS
    ৫
    1.93
    ется
    1.89
    ت
    1.66
    ني
    1.57
    し
    1.57
    ри
    1.53
    ции
    1.52
    تهم
    1.48
    اکي
    1.47
    ۵
    1.45
    Activations Density 0.001%

    No Known Activations