© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215963
    Prev
    Next
    INDEX
    Explanations

    todo completion

    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_31_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
     também
    0.46
    하고
    0.46
     arī
    0.45
    &&(
    0.45
    &&
    0.44
    ocysts
    0.44
     bağlant
    0.43
     भी
    0.42
     decreto
    0.42
    hbs
    0.41
    POSITIVE LOGITS
     sowie
    0.45
     sekä
    0.41
     serta
    0.39
     samt
    0.36
     oraz
    0.35
    끌
    0.34
    älte
    0.34
     successful
    0.34
    เช่น
    0.33
     সম্পূর্ণরূপে
    0.33
    Activations Density 0.000%

    No Known Activations