© 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. 170899
    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
     OFF
    0.49
    ได้รับ
    0.45
     Salon
    0.44
    TERY
    0.43
     forums
    0.42
    URNS
    0.42
     lanterns
    0.41
     "-",
    0.41
     pharmacies
    0.40
     ترلاسه
    0.40
    POSITIVE LOGITS
    thia
    0.44
    ríklad
    0.44
    ви
    0.44
    継続
    0.44
     mengembangkan
    0.44
     utveck
    0.43
    циа
    0.43
    BackendAuth
    0.43
     необходимость
    0.43
     gelişt
    0.42
    Activations Density 0.000%

    No Known Activations