© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157040
    Prev
    Next
    INDEX
    Explanations

    capnography

    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_2_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
    м
    1.13
    ى
    1.10
    م
    1.05
    ?
    1.05
    り
    0.97
    ง
    0.96
    ം
    0.96
    et
    0.95
    ни
    0.95
    తో
    0.94
    POSITIVE LOGITS
     in
    1.65
     of
    1.32
    f
    1.26
    T
    1.11
     on
    1.09
    Y
    1.09
    D
    1.09
    O
    1.05
    ד
    0.98
     পরিমাণ
    0.98
    Activations Density 0.002%

    No Known Activations