© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116181
    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_27_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
     तीन
    0.44
     మూడు
    0.39
    三次
    0.39
     बिजली
    0.37
    <unused3>
    0.37
     історії
    0.36
    Clothes
    0.36
    บอล
    0.35
    <unused15>
    0.35
     истории
    0.35
    POSITIVE LOGITS
    ptr
    0.37
    aterina
    0.36
    IMS
    0.35
    forall
    0.35
     NONCLUSTERED
    0.34
    智能
    0.34
    するとき
    0.34
     पट
    0.33
     desperately
    0.33
    kada
    0.33
    Activations Density 0.000%

    No Known Activations