© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197075
    Prev
    Next
    INDEX
    Explanations

    Spectre, Talon, brush

    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
    {
    0.56
    괘
    0.52
    <b>
    0.51
     abril
    0.51
     Transporte
    0.50
    ଡ
    0.50
     назнача
    0.49
    휙
    0.49
    ОВ
    0.49
    ٦
    0.48
    POSITIVE LOGITS
    ci
    0.70
    in
    0.63
    te
    0.63
    al
    0.59
    er
    0.56
    va
    0.56
    es
    0.56
    ma
    0.55
    tu
    0.54
    ul
    0.54
    Activations Density 0.000%

    No Known Activations