© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258995
    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_22_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
    azier
    0.45
     ஆண்டுக
    0.45
     Scholz
    0.44
    asil
    0.43
     এরপর
    0.43
     sesuai
    0.43
    CONNECTED
    0.42
     ե
    0.42
    ডিং
    0.42
     ук
    0.42
    POSITIVE LOGITS
    ت
    0.59
    люб
    0.55
    두
    0.54
    是
    0.54
    وم
    0.50
    نز
    0.49
    élev
    0.49
    이블
    0.48
    样的
    0.47
    ک
    0.47
    Activations Density 0.000%

    No Known Activations