© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194002
    Prev
    Next
    INDEX
    Explanations

    Hartford, Worcester, Hertz, over

    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_9_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
    c
    0.94
    p
    0.80
    on
    0.75
    ação
    0.70
    ا
    0.68
    på
    0.67
    it
    0.64
     it
    0.63
    ligere
    0.62
    mals
    0.61
    POSITIVE LOGITS
    м
    0.95
    ли
    0.84
    UT
    0.80
    没有什么
    0.78
     Bentham
    0.77
    ת
    0.77
     Göttingen
    0.77
     five
    0.77
     Berber
    0.77
    ع
    0.76
    Activations Density 0.000%

    No Known Activations