© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164430
    Prev
    Next
    INDEX
    Explanations

    dedicated to

    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_13_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
    ن
    0.26
    Very
    0.26
    Fluid
    0.26
    هو
    0.25
    ש
    0.25
    سة
    0.25
    $.
    0.24
    تك
    0.24
     weil
    0.24
    ;
    0.24
    POSITIVE LOGITS
     могла
    0.27
     romances
    0.26
     थेट
    0.26
     Доб
    0.25
     Kut
    0.24
     произведения
    0.24
     Burgers
    0.24
     Grenoble
    0.24
    anya
    0.24
     vadanti
    0.24
    Activations Density 0.005%

    No Known Activations