© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124996
    Prev
    Next
    INDEX
    Explanations

    gstreamer

    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
    c
    0.79
    б
    0.68
     garanti
    0.63
     créée
    0.62
     resolve
    0.62
     controla
    0.62
    д
    0.61
    ز
    0.61
     evita
    0.60
     componente
    0.60
    POSITIVE LOGITS
    -
    0.92
    '
    0.79
    lene
    0.68
    lum
    0.67
    nitz
    0.65
    urik
    0.65
    n
    0.64
    nickel
    0.63
     I
    0.63
    ll
    0.63
    Activations Density 0.000%

    No Known Activations