© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90730
    Prev
    Next
    INDEX
    Explanations

    way

    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
    桎
    0.65
    ビ
    0.64
    ದು
    0.59
     ይጠ
    0.58
    цију
    0.58
    ጥረ
    0.57
     допол
    0.55
    fireFlower
    0.55
     مور
    0.55
     الگ
    0.55
    POSITIVE LOGITS
    '
    0.87
     and
    0.81
     .
    0.67
    h
    0.64
     Following
    0.63
     Ats
    0.63
     And
    0.62
     Year
    0.62
     $
    0.61
     YEAR
    0.61
    Activations Density 0.001%

    No Known Activations