© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163571
    Prev
    Next
    INDEX
    Explanations

    satellite resolution

    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_13_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
    री
    0.42
     питання
    0.38
     분야
    0.37
    츠
    0.36
     চৈতন্য
    0.36
    จังหวัด
    0.36
    อรี่
    0.36
     perguntas
    0.35
     ভাঁ
    0.35
     Fragen
    0.35
    POSITIVE LOGITS
     Ä
    0.45
    four
    0.44
     arv
    0.43
     आएगा
    0.41
     Buon
    0.40
     desean
    0.40
     Toulouse
    0.39
     beş
    0.39
    ধীন
    0.39
     zej
    0.39
    Activations Density 0.013%

    No Known Activations