© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210793
    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_20_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
    сова
    0.46
     vendido
    0.46
    <td>
    0.44
     slats
    0.42
     beverages
    0.42
     regul
    0.41
     pricey
    0.41
     reprezent
    0.41
     pretzels
    0.41
    alá
    0.40
    POSITIVE LOGITS
     تلویزی
    0.47
    ghed
    0.46
    ccnc
    0.44
     மாவ
    0.44
    maligngroup
    0.44
    侎
    0.44
    ίκη
    0.44
    电视
    0.43
    ધી
    0.43
    गा
    0.42
    Activations Density 0.000%

    No Known Activations