© 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. 38024
    Prev
    Next
    INDEX
    Explanations

    topic modeling literature

    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
    めちゃ
    0.62
    ﻪ
    0.60
     katana
    0.59
    “
    0.59
    ه
    0.58
    }
    0.58
    岧
    0.58
    처럼
    0.57
     التربيع
    0.57
    ன்
    0.57
    POSITIVE LOGITS
     a
    1.12
     of
    0.88
     on
    0.82
    ka
    0.72
    ko
    0.72
     ของ
    0.71
    на
    0.70
     của
    0.70
    .
    0.68
     to
    0.66
    Activations Density 0.001%

    No Known Activations