© 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. 138439
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    il
    0.61
    _
    0.57
    hi
    0.54
    ilot
    0.54
    {(\
    0.54
     communaut
    0.54
    noof
    0.52
    jahter
    0.51
     Eater
    0.51
    heer
    0.50
    POSITIVE LOGITS
    手臂
    0.54
    ARA
    0.50
     flanges
    0.49
    𝗘
    0.48
    Vinyl
    0.48
     genç
    0.47
    ARS
    0.47
     בן
    0.47
    ROSS
    0.47
    𝖊
    0.47
    Activations Density 0.000%

    No Known Activations