© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82850
    Prev
    Next
    INDEX
    Explanations

    neo or line

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     T
    0.46
     tra
    0.41
    ත්‍ර
    0.39
    ામ
    0.39
    Cast
    0.39
    ræ
    0.38
     भूषण
    0.38
    飾
    0.38
    cast
    0.37
     Tra
    0.37
    POSITIVE LOGITS
     प्रोट
    0.41
     Prototype
    0.39
     கி
    0.38
     Beam
    0.37
     Carpent
    0.37
     প্রদ
    0.36
     Nutrient
    0.36
    哴
    0.36
    han
    0.36
     ದಾ
    0.35
    Activations Density 0.005%

    No Known Activations