© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134851
    Prev
    Next
    INDEX
    Explanations

    spectroscopy, structure, theory, DFT calculations

    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
    er
    1.17
    al
    1.15
    וף
    1.02
    at
    1.00
     (
    0.98
     que
    0.96
     a
    0.92
    ↵↵↵
    0.88
    هِ
    0.88
    in
    0.88
    POSITIVE LOGITS
     коды
    0.93
     интерес
    0.87
     انگ
    0.87
     목적
    0.87
     источников
    0.87
     সংখ্য
    0.85
     인한
    0.85
     имена
    0.85
     숫자
    0.84
    ປະ
    0.84
    Activations Density 0.009%

    No Known Activations