© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14725
    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_40_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
     ROOT
    0.45
     Déf
    0.41
     Planning
    0.37
     ኢ
    0.37
    وہ
    0.36
     बाय
    0.36
     planificación
    0.35
     IRE
    0.35
     話
    0.35
    慈
    0.35
    POSITIVE LOGITS
    legends
    0.44
     जीके
    0.42
    arki
    0.42
     सके
    0.38
    кг
    0.38
    enso
    0.38
     леген
    0.37
     parcels
    0.37
    estro
    0.36
     Kelsey
    0.36
    Activations Density 0.000%

    No Known Activations