© 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. 44145
    Prev
    Next
    INDEX
    Explanations

    URL starts with https://

    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
     нужно
    0.67
     {
    0.64
    ين
    0.61
    н
    0.60
     состояния
    0.60
    ຯ
    0.59
     *
    0.57
    dır
    0.57
     astonishing
    0.56
     opposites
    0.56
    POSITIVE LOGITS
    ри
    0.96
    、「
    0.75
    </h3>
    0.70
    ।
    0.68
    、
    0.68
    ัน
    0.65
    ）。
    0.63
    om
    0.63
    ）、
    0.63
    yl
    0.62
    Activations Density 0.017%

    No Known Activations