© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11837
    Prev
    Next
    INDEX
    Explanations

    that feedback

    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_13_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
    m
    0.46
    t
    0.46
     not
    0.45
    Not
    0.41
    not
    0.39
    k
    0.38
    x
    0.38
    =
    0.38
     тот
    0.37
    =.
    0.36
    POSITIVE LOGITS
     있던
    0.41
    iapan
    0.37
    adakan
    0.36
    烺
    0.36
     кампа
    0.35
    协同
    0.35
     évek
    0.35
    ură
    0.34
    produkt
    0.34
     җиңү
    0.33
    Activations Density 0.025%

    No Known Activations