© 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. 258061
    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
    카오
    0.48
     Quarter
    0.47
    फुल
    0.44
     midrange
    0.44
     eprintln
    0.44
     reak
    0.44
     sit
    0.43
     *>(
    0.42
     ['<%=
    0.42
     limit
    0.42
    POSITIVE LOGITS
    ain
    0.54
    知識
    0.53
    اک
    0.52
    ais
    0.51
     connaissance
    0.50
    PDF
    0.48
    鐪
    0.48
    ös
    0.45
    ff
    0.45
    вър
    0.45
    Activations Density 0.000%

    No Known Activations