© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88031
    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_23_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
    ול
    0.45
    Dul
    0.41
    㸽
    0.41
    \$
    0.41
    son
    0.40
    gress
    0.39
    helmet
    0.39
    maar
    0.39
    教
    0.38
    olar
    0.38
    POSITIVE LOGITS
     робити
    0.41
     கண்டிப்பாக
    0.40
     Сегодня
    0.39
     වර්ග
    0.39
     พระ
    0.38
     всички
    0.38
     Сьогодні
    0.38
     リビング
    0.37
     আজকে
    0.37
     里
    0.37
    Activations Density 0.000%

    No Known Activations