© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205128
    Prev
    Next
    INDEX
    Explanations

    operators

    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
    }}^{*}\
    0.41
    の実
    0.40
     элементы
    0.39
     ਸ਼
    0.38
     राधे
    0.38
     ర
    0.36
     wickedness
    0.36
     Curves
    0.36
    沱
    0.36
     आंकड़ों
    0.35
    POSITIVE LOGITS
     Portion
    0.42
    ijom
    0.41
     portion
    0.41
    Me
    0.40
    portion
    0.40
     Proportion
    0.40
     employing
    0.39
    संग
    0.39
     Lans
    0.39
     portions
    0.38
    Activations Density 0.001%

    No Known Activations