© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48434
    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_10_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
    Pride
    0.61
    ᗜ
    0.57
     Piotr
    0.55
    Transc
    0.53
    یعنی
    0.52
    Gior
    0.50
    ∀
    0.50
    𒊏
    0.49
    برای
    0.49
    ᑉ
    0.49
    POSITIVE LOGITS
     sneaky
    0.52
     disposable
    0.50
     toxic
    0.50
     null
    0.49
     mixtures
    0.48
    elés
    0.48
     horse
    0.45
     注意
    0.44
     muddy
    0.44
     grievances
    0.44
    Activations Density 0.000%

    No Known Activations