© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205211
    Prev
    Next
    INDEX
    Explanations

    say "arial"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    hö
    0.39
    ಾನ
    0.37
    teman
    0.37
    listening
    0.36
    Collabor
    0.36
    φορά
    0.36
    ําน
    0.35
    헉
    0.35
     complying
    0.34
    hrung
    0.34
    POSITIVE LOGITS
     aire
    0.65
     AIR
    0.63
     Aire
    0.63
    aire
    0.61
    Aer
    0.61
     Aer
    0.61
    aer
    0.61
     aeration
    0.61
    AIR
    0.60
     aerial
    0.59
    Activations Density 0.001%

    No Known Activations