© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130587
    Prev
    Next
    INDEX
    Explanations

    brainstorming or discussing ideas

    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_1_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
    the
    1.05
    ।
    1.02
    dan
    1.00
    st
    0.98
    ۔
    0.94
    。
    0.91
    needed
    0.89
    t
    0.89
    ﺪ
    0.88
    ۵
    0.88
    POSITIVE LOGITS
    '
    1.34
    ’
    1.09
    то
    1.00
    ಾ
    1.00
    ak
    0.91
    ’”
    0.88
    ਾ
    0.87
    써
    0.86
     caveats
    0.85
    '/>
    0.85
    Activations Density 0.003%

    No Known Activations