© 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. 40452
    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
    停止
    0.48
     water
    0.47
    Captain
    0.47
    ountains
    0.47
     #{@
    0.46
     Captain
    0.46
     другие
    0.45
     água
    0.45
     然后
    0.45
    但
    0.45
    POSITIVE LOGITS
    ка
    0.60
    рь
    0.50
    сла
    0.49
    джи
    0.47
    faz
    0.46
    ikon
    0.46
    ग्रह
    0.45
    форми
    0.44
    retta
    0.44
    в
    0.44
    Activations Density 0.000%

    No Known Activations