© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217439
    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_31_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
     कॉम्प
    0.49
    孱
    0.44
    டியான
    0.38
    谠
    0.38
     طی
    0.38
    lblCredits
    0.38
     компью
    0.38
    𐰑
    0.37
     լ
    0.37
     harapan
    0.36
    POSITIVE LOGITS
     simultaneous
    0.38
     cluster
    0.36
     possible
    0.36
     Cuts
    0.36
    elier
    0.35
     Serge
    0.35
     under
    0.33
     Correspond
    0.33
     Simultaneously
    0.33
     Buk
    0.33
    Activations Density 0.000%

    No Known Activations