© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154200
    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
    izzo
    0.41
    ே
    0.37
     /
    0.37
    ீ
    0.35
     -
    0.34
    isu
    0.34
     đẳng
    0.34
    CO
    0.34
     precious
    0.33
    일
    0.33
    POSITIVE LOGITS
     ज्‍यादा
    0.44
    聵
    0.43
     dined
    0.42
    েন্ত্র
    0.42
     substituted
    0.42
    がお
    0.41
    𝗿
    0.40
     বেগ
    0.40
    ষ্টিত
    0.40
     பகுதிக
    0.40
    Activations Density 0.000%

    No Known Activations