© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258997
    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_22_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
     elastomer
    0.47
     oracle
    0.46
     ekran
    0.44
     brz
    0.44
     alphan
    0.43
     選
    0.43
    원에서
    0.43
     accelerator
    0.42
     লাইন
    0.42
    럭
    0.42
    POSITIVE LOGITS
    ého
    0.51
    et
    0.50
     warrantless
    0.50
    goài
    0.48
    at
    0.47
    ar
    0.46
    ̉a
    0.46
    ế
    0.46
     Georgian
    0.46
    бя
    0.44
    Activations Density 0.000%

    No Known Activations