© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29099
    Prev
    Next
    INDEX
    Explanations

    rate at which

    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_10_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
     C
    0.21
    Deg
    0.21
    ння
    0.21
    ى
    0.21
    ighed
    0.21
    我們
    0.20
    ън
    0.20
    و
    0.20
    我们也
    0.20
     Deg
    0.19
    POSITIVE LOGITS
    the
    0.26
    ۔
    0.23
     malicious
    0.23
    d
    0.23
    ።
    0.22
    ​.
    0.22
    .
    0.22
     poppies
    0.21
    s
    0.21
    EN
    0.21
    Activations Density 0.007%

    No Known Activations