© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48517
    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_31_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
    คองโก
    0.39
     जमिनी
    0.38
    clay
    0.37
     карто
    0.37
    땅
    0.37
    wh
    0.35
    व्
    0.35
     Pann
    0.35
    acido
    0.35
     intention
    0.35
    POSITIVE LOGITS
     Adv
    0.39
     Vide
    0.38
    Adv
    0.38
    humidity
    0.37
    ⁰
    0.36
     বিস্ত
    0.35
    તું
    0.35
     گم
    0.35
    ுள்ளது
    0.35
    বিস্ত
    0.35
    Activations Density 0.000%

    No Known Activations