© 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. 171614
    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
    سة
    0.52
    Prothorax
    0.47
    commande
    0.47
    গামী
    0.46
    Benzoimidazol
    0.46
    examen
    0.46
    ⎦
    0.45
    ገለ
    0.45
     клеток
    0.45
     從
    0.44
    POSITIVE LOGITS
     are
    0.59
     on
    0.54
    ile
    0.52
     is
    0.50
     ovat
    0.47
    enary
    0.46
    励
    0.46
     at
    0.45
     tying
    0.45
    явля
    0.45
    Activations Density 0.000%

    No Known Activations