© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 197309
    Prev
    Next
    INDEX
    Explanations

    Mausoleum, progressive experience

    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_15_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
    ol
    0.76
    m
    0.71
    r
    0.68
    t
    0.61
    g
    0.61
    գ
    0.59
     khí
    0.57
     -
    0.56
    on
    0.55
    H
    0.55
    POSITIVE LOGITS
     poderão
    0.60
    !);
    0.56
     드리
    0.52
     Podemos
    0.51
     DIGITAL
    0.49
    🛐
    0.49
     atti
    0.48
    인을
    0.48
    Calling
    0.47
    Channels
    0.47
    Activations Density 0.000%

    No Known Activations