© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37592
    Prev
    Next
    INDEX
    Explanations

    pretty sure

    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_11_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
     è
    0.67
     année
    0.63
     intérêt
    0.63
     être
    0.59
     ć
    0.56
     ทำ
    0.55
     年
    0.55
     carina
    0.55
     sa
    0.54
    ić
    0.54
    POSITIVE LOGITS
    ן
    0.48
    occo
    0.46
    ક્રિય
    0.44
    crash
    0.44
    কোষ
    0.44
    了他的
    0.44
    רג
    0.43
    iffo
    0.42
    ну
    0.42
     বজ্র
    0.41
    Activations Density 0.000%

    No Known Activations