© 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. 41724
    Prev
    Next
    INDEX
    Explanations

    part numbers containing letters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Visual
    0.41
    決
    0.38
    Finland
    0.37
    potential
    0.36
    気が
    0.36
    併
    0.36
    به
    0.36
    潛
    0.36
    Estimated
    0.36
    Pokémon
    0.36
    POSITIVE LOGITS
     Charity
    0.44
     courte
    0.42
     parmi
    0.41
     Hương
    0.40
     oczywiście
    0.40
     principalColumn
    0.40
     danh
    0.40
     Marcello
    0.40
    کروچ
    0.39
    elled
    0.39
    Activations Density 0.004%

    No Known Activations