© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39274
    Prev
    Next
    INDEX
    Explanations

    Ctrl+

    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_3_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
     convoluted
    0.91
     impasse
    0.71
    n
    0.69
     investigative
    0.66
     tabular
    0.66
     heady
    0.65
     disastrous
    0.64
     deceptive
    0.64
     agglut
    0.64
     piggy
    0.63
    POSITIVE LOGITS
    1
    1.02
    5
    0.83
    Sh
    0.77
    K
    0.75
    Nil
    0.74
    3
    0.73
    Error
    0.71
    Controllers
    0.70
    9
    0.70
    Element
    0.68
    Activations Density 0.002%

    No Known Activations