© 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. 249485
    Prev
    Next
    INDEX
    Explanations

    Physical

    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
     Middle
    0.46
     Sub
    0.40
     Full
    0.40
     R
    0.40
     Pro
    0.40
    cohols
    0.39
     Great
    0.38
    R
    0.38
    Middle
    0.38
     Pul
    0.38
    POSITIVE LOGITS
    ity
    1.50
    ITY
    1.18
    ता
    0.61
    сть
    0.57
    なって
    0.55
    ness
    0.49
    なります
    0.45
    िटी
    0.44
     الاست
    0.44
     Ста
    0.44
    Activations Density 0.003%

    No Known Activations