© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205836
    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_6_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
    ك
    1.52
    ка
    1.16
    о
    1.11
     e
    1.09
    ↵
    1.06
     you
    1.02
     r
    1.02
    ata
    1.00
    *,
    0.99
    out
    0.98
    POSITIVE LOGITS
     impuestos
    1.20
    itism
    1.15
     microns
    1.10
     iguales
    1.05
     astrocytes
    1.03
     categorias
    1.01
     inverses
    1.00
     inversiones
    1.00
     imputed
    1.00
     ensembles
    1.00
    Activations Density 0.000%

    No Known Activations