© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46206
    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_13_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
    ؕ
    0.48
    ፴
    0.48
    命中
    0.46
     versuchen
    0.45
    諳
    0.45
     domicilio
    0.44
     بیټ
    0.44
    卡的
    0.43
    ầm
    0.43
    訌
    0.43
    POSITIVE LOGITS
     parli
    0.49
    宽
    0.46
     ingred
    0.44
     reasons
    0.44
     zami
    0.43
    ствия
    0.42
     -
    0.42
     ta
    0.42
     बाजारों
    0.42
    yoruz
    0.42
    Activations Density 0.000%

    No Known Activations