© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202182
    Prev
    Next
    INDEX
    Explanations

    wind tunnels and testing

    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_12_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
    ر
    0.64
     или
    0.58
     د
    0.53
    начала
    0.53
    䚲
    0.52
    или
    0.52
     وهنا
    0.52
    或者
    0.51
     proguardFiles
    0.51
    لنا
    0.50
    POSITIVE LOGITS
    ;
    0.49
    acid
    0.47
    in
    0.47
    all
    0.46
     theatres
    0.45
    相対
    0.45
    k
    0.44
    insensitive
    0.44
    add
    0.44
     dragged
    0.44
    Activations Density 0.000%

    No Known Activations