© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200185
    Prev
    Next
    INDEX
    Explanations

    Dep

    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_46_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
    彬
    0.41
    吉
    0.40
    জ্জিত
    0.39
    lEdit
    0.38
     регулярно
    0.38
    \[
    0.37
    unjukkan
    0.37
    /**/*
    0.37
    kort
    0.37
    ensuche
    0.37
    POSITIVE LOGITS
     material
    0.52
     Material
    0.51
    material
    0.48
    Material
    0.45
     материа
    0.44
     матеріа
    0.43
     料
    0.40
     materiality
    0.40
     MATERIAL
    0.38
     мате
    0.38
    Activations Density 0.005%

    No Known Activations