© 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. 90450
    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_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
     hypot
    0.51
     экологи
    0.48
     брига
    0.46
     محیط
    0.46
    dim
    0.46
    raz
    0.45
    我
    0.45
     мили
    0.45
    oss
    0.44
     ecológica
    0.43
    POSITIVE LOGITS
    璈
    0.55
     lena
    0.51
    দ্যাল
    0.48
    Jas
    0.47
    شون
    0.47
    рија
    0.46
    ایج
    0.46
    ठमाडौं
    0.46
    謳
    0.46
     הייתה
    0.46
    Activations Density 0.000%

    No Known Activations