© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33715
    Prev
    Next
    INDEX
    Explanations

    guest reviews and speakers

    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_3_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
     guest
    0.65
    н
    0.64
    th
    0.59
    na
    0.59
    น
    0.59
    no
    0.58
     Guest
    0.57
    not
    0.57
    re
    0.56
    தன
    0.56
    POSITIVE LOGITS
    ب
    0.71
    ز
    0.70
    wj
    0.60
    зира
    0.58
    ру
    0.57
    числи
    0.57
    Seqs
    0.57
     मंत्रि
    0.55
    きた
    0.54
     त्वरित
    0.54
    Activations Density 0.001%

    No Known Activations