© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82893
    Prev
    Next
    INDEX
    Explanations

    say "."

    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_53_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
    Ml
    0.41
    diver
    0.39
     Execute
    0.39
    turbo
    0.39
    大量
    0.38
    Боль
    0.38
     Tä
    0.38
    鼗
    0.38
    Alder
    0.36
    Phys
    0.36
    POSITIVE LOGITS
     manipulating
    0.39
     postgraduate
    0.38
     east
    0.37
     rata
    0.37
     defeating
    0.37
     communism
    0.37
     offset
    0.36
    geny
    0.36
     revisiting
    0.35
     князя
    0.35
    Activations Density 0.001%

    No Known Activations