© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63237
    Prev
    Next
    INDEX
    Explanations

    aircraft controls

    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_59_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
     tail
    0.59
    tail
    0.49
    Tail
    0.48
    tails
    0.45
     tails
    0.45
    Wings
    0.44
    尾
    0.43
     Tail
    0.42
     Wings
    0.39
    門
    0.39
    POSITIVE LOGITS
     r
    0.59
     بعد
    0.54
     after
    0.50
     dopo
    0.48
     р
    0.47
     ر
    0.47
     después
    0.47
     після
    0.45
     после
    0.42
    зона
    0.42
    Activations Density 0.002%

    No Known Activations