© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89002
    Prev
    Next
    INDEX
    Explanations

    write code examples

    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_18_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
     exercícios
    0.54
     endometriosis
    0.45
     Throw
    0.43
    asitriangular
    0.42
     التمرين
    0.41
     FCM
    0.40
    
    0.39
     darn
    0.39
     exercício
    0.39
    exercice
    0.39
    POSITIVE LOGITS
    י
    0.49
     monolith
    0.48
    א
    0.48
     renamed
    0.46
    UP
    0.43
     customizable
    0.43
    وک
    0.43
    IS
    0.43
    挟
    0.42
    UPA
    0.42
    Activations Density 0.000%

    No Known Activations