© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1478
    Prev
    Next
    INDEX
    Explanations

    Science, education, innovation, technology, government

    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_39_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
    Diffuse
    0.40
     கால்
    0.39
    衢
    0.38
    Stein
    0.35
    Pant
    0.35
     suo
    0.35
    мей
    0.35
    陬
    0.34
     қ
    0.34
    otea
    0.34
    POSITIVE LOGITS
     science
    0.47
     ciencia
    0.43
     과학
    0.43
     наука
    0.42
     innovation
    0.42
     SCIENCE
    0.42
     нау
    0.41
     Science
    0.40
     அறிவியல்
    0.40
     науки
    0.39
    Activations Density 0.020%

    No Known Activations