© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157917
    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_2_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
    Predict
    0.56
    "};
    0.55
    预测
    0.53
    B
    0.52
    ";
    0.51
    Cotton
    0.51
    WOOD
    0.50
    predict
    0.48
    જાર
    0.47
    ");
    0.47
    POSITIVE LOGITS
     Armin
    0.48
     pathos
    0.47
    mySocket
    0.46
     toj
    0.46
    ěji
    0.46
    ارع
    0.44
     Акы
    0.44
    ᓃ
    0.44
     isti
    0.43
    르게
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.