© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116927
    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
    茷
    0.39
    мено
    0.39
     dignit
    0.36
    </td>
    0.36
    畤
    0.35
    ческого
    0.35
    動物
    0.35
     siedz
    0.34
    
    0.34
    seign
    0.34
    POSITIVE LOGITS
     crunchy
    0.43
     αυτά
    0.42
     மாட்ட
    0.41
     Bracelet
    0.41
     milliseconds
    0.40
     bracelets
    0.40
     Unicorn
    0.40
    track
    0.40
    ʼn
    0.40
     pickles
    0.40
    Activations Density 0.000%

    No Known Activations