© 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. 36110
    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
     права
    0.46
    гы
    0.46
    多次
    0.45
    p
    0.45
    ，
    0.43
     ziehen
    0.43
     draws
    0.41
     zeich
    0.41
    熏
    0.41
     لهذا
    0.41
    POSITIVE LOGITS
    Uh
    0.54
    וה
    0.50
    Neck
    0.46
     reduce
    0.46
    uffled
    0.46
     Reduce
    0.45
    igere
    0.45
    ða
    0.45
     ربعه
    0.45
    UpperCase
    0.45
    Activations Density 0.000%

    No Known Activations