© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50576
    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_30_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
    㬰
    0.39
    fois
    0.38
    ୁ
    0.38
     Balfour
    0.38
    MappingURL
    0.37
     Uran
    0.37
     indifference
    0.36
     meditative
    0.36
     अवल
    0.36
     វា
    0.35
    POSITIVE LOGITS
    faat
    0.47
    鑷
    0.40
     Styles
    0.40
    feer
    0.38
     пол
    0.38
    яти
    0.37
    ارك
    0.37
    gia
    0.37
     இய
    0.36
    agnie
    0.36
    Activations Density 0.000%

    No Known Activations