© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47434
    Prev
    Next
    INDEX
    Explanations

    command descriptions and usage

    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
     for
    0.82
    I
    0.81
    0
    0.78
    </b>
    0.74
    0.73
    t
    0.71
    <0x0D>
    0.70
    </h2>
    0.70
    ers
    0.67
    Was
    0.66
    POSITIVE LOGITS
     voisins
    0.75
    д
    0.72
     ټینس
    0.71
    ↵↵
    0.71
     enseign
    0.71
     pouze
    0.69
     rů
    0.68
     upravo
    0.68
     металла
    0.66
     passwords
    0.66
    Activations Density 0.022%

    No Known Activations