© 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. 24946
    Prev
    Next
    INDEX
    Explanations

    what exactly is

    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
    le
    1.03
    il
    0.91
    an
    0.89
    la
    0.84
    ine
    0.84
    ast
    0.77
    ad
    0.76
    c
    0.76
    ers
    0.75
    l
    0.75
    POSITIVE LOGITS
    I
    0.86
    BufOffset
    0.85
    います
    0.70
    Warum
    0.69
    קר
    0.68
    شى
    0.67
    ).$$
    0.67
    。)
    0.67
    Nicht
    0.63
    IUpdate
    0.62
    Activations Density 0.019%

    No Known Activations