© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237109
    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_32_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
    indeed
    0.39
    㩴
    0.38
    本当に
    0.38
     বাড়ী
    0.38
     margins
    0.37
     실제로
    0.37
     shooter
    0.36
     действительно
    0.36
     interception
    0.36
     ю
    0.36
    POSITIVE LOGITS
    CTest
    0.39
     ಪಕ್ಷ
    0.37
     Verd
    0.36
     Muy
    0.36
    Finished
    0.35
    )))))
    0.35
    वादी
    0.34
     Carn
    0.34
     Charlene
    0.34
     Pensacola
    0.34
    Activations Density 0.000%

    No Known Activations