© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 137173
    Prev
    Next
    INDEX
    Explanations

    api keys and instrumentation

    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_37_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
     الشيء
    0.39
    Taxi
    0.37
    &=
    0.35
    ][_
    0.35
     Noi
    0.35
    ʽ
    0.35
    編輯
    0.34
    㥆
    0.34
    Teacher
    0.34
    delegate
    0.34
    POSITIVE LOGITS
    公
    0.46
     nightly
    0.40
     Acer
    0.40
     Pub
    0.38
     Shea
    0.38
     သင်
    0.38
     Jenner
    0.37
     Ingram
    0.37
     Bor
    0.37
    Shea
    0.37
    Activations Density 0.001%

    No Known Activations