© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200892
    Prev
    Next
    INDEX
    Explanations

    German "bew" prefix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     закры
    1.46
     closing
    1.44
     closed
    1.43
     closes
    1.41
    closing
    1.40
    閉
    1.38
     Closing
    1.37
    Closing
    1.36
    闭
    1.35
    Closed
    1.30
    POSITIVE LOGITS
     bew
    1.06
    Bew
    0.80
    bew
    0.79
     Bew
    0.68
     Lew
    0.50
    Lew
    0.46
    vox
    0.41
    ewa
    0.40
     beads
    0.39
     bewe
    0.39
    Activations Density 0.011%

    No Known Activations