© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123761
    Prev
    Next
    INDEX
    Explanations

    sandcastles and beaches

    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
    .,
    0.59
     alkaloids
    0.58
    .
    0.58
     (
    0.58
    are
    0.57
     sprinter
    0.56
     [
    0.55
    ס
    0.55
     och
    0.55
    al
    0.54
    POSITIVE LOGITS
    годи
    0.62
     QSO
    0.61
    ру
    0.59
     QSOs
    0.59
    вим
    0.56
    рт
    0.56
    のカ
    0.55
    टिक
    0.55
     XPS
    0.54
    លើ
    0.53
    Activations Density 0.001%

    No Known Activations