© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196407
    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_27_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
     '{
    0.35
     শ্রেণি
    0.34
    ];
    0.33
    '$\
    0.33
    '];
    0.33
     institucional
    0.33
    <0x19>
    0.32
    ="'
    0.32
     aspirants
    0.32
     jTextField
    0.32
    POSITIVE LOGITS
    每次
    0.34
     էին
    0.34
    studded
    0.34
    ಿಕೊಂಡ
    0.33
     souhaitez
    0.33
    chez
    0.33
    thres
    0.33
     outlandish
    0.33
     derin
    0.32
    ುತ್ತೇನೆ
    0.32
    Activations Density 0.000%

    No Known Activations