© 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. 42886
    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
     maneiras
    0.42
     Finish
    0.41
    <0x84>
    0.40
    ˆ
    0.39
     Industries
    0.38
     Finder
    0.38
     PartialEq
    0.38
    ∧
    0.37
     Last
    0.37
     Fraction
    0.37
    POSITIVE LOGITS
     ಫಲ
    0.51
     prevent
    0.50
    јединачна
    0.50
     facem
    0.49
    एनजी
    0.49
    %,
    0.49
    рби
    0.48
     petroleum
    0.47
    ’),
    0.46
    ября
    0.46
    Activations Density 0.000%

    No Known Activations