© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202682
    Prev
    Next
    INDEX
    Explanations

    treated with

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     équipes
    1.10
    3
    1.06
    ।
    0.98
    8
    0.96
     più
    0.92
    ів
    0.91
     parecía
    0.88
    Secondo
    0.88
     który
    0.88
     беше
    0.87
    POSITIVE LOGITS
    ل
    1.05
    л
    1.01
    िल
    0.92
    ह
    0.82
    葲
    0.80
    好
    0.79
    ona
    0.77
    scopic
    0.77
    erequisite
    0.77
    ledad
    0.76
    Activations Density 0.001%

    No Known Activations