© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40624
    Prev
    Next
    INDEX
    Explanations

    Design and optimization experiments

    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_11_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
    ؛
    0.65
     flip
    0.59
    ،
    0.58
     Humidity
    0.55
     Flip
    0.55
     bài
    0.54
    Flip
    0.53
     Fli
    0.53
    ;
    0.52
     ؛
    0.50
    POSITIVE LOGITS
     коро
    0.53
    вна
    0.53
    ζεται
    0.52
    enek
    0.52
    isely
    0.52
    сну
    0.51
    сей
    0.50
    inė
    0.48
    рна
    0.48
    ä
    0.48
    Activations Density 0.007%

    No Known Activations