© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162666
    Prev
    Next
    INDEX
    Explanations

    book titles and academic subjects

    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_31_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
    Docket
    0.40
    resher
    0.36
    〠
    0.34
    ິນ
    0.34
     അക
    0.33
     Pensacola
    0.33
     ধরা
    0.32
     apical
    0.31
    到来
    0.31
     наста
    0.31
    POSITIVE LOGITS
    믹
    0.45
     വിവ
    0.42
    امام
    0.41
    ֛
    0.38
     demon
    0.37
     uncover
    0.37
    ವರೆ
    0.37
     investigate
    0.37
     uncovered
    0.36
    isu
    0.36
    Activations Density 0.001%

    No Known Activations