© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17120
    Prev
    Next
    INDEX
    Explanations

    libraries and librarians

    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_40_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
    اندی
    0.45
     bottling
    0.42
    zecz
    0.38
     communique
    0.38
    iant
    0.38
     Jamal
    0.36
     भुजा
    0.36
    ᱧ
    0.36
     ಹಣ
    0.35
    猬
    0.35
    POSITIVE LOGITS
     library
    2.84
     libraries
    2.70
     Library
    2.56
     Libraries
    2.53
    Library
    2.42
     библиоте
    2.42
    library
    2.41
    Libraries
    2.39
     библиотеки
    2.36
     бібліоте
    2.34
    Activations Density 0.081%

    No Known Activations