© 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. 216139
    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_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
     Vort
    0.45
     cosmetology
    0.40
    ACS
    0.39
    ೀಯ
    0.39
     machin
    0.39
     Locate
    0.39
     abhiv
    0.39
    階
    0.39
    skom
    0.38
    locate
    0.38
    POSITIVE LOGITS
    imer
    0.45
    ревнования
    0.38
     underlined
    0.37
     Im
    0.37
    awa
    0.36
     Lith
    0.36
    imetric
    0.36
    Gesture
    0.36
     বাহিনী
    0.35
    `,
    0.34
    Activations Density 0.000%

    No Known Activations