© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196427
    Prev
    Next
    INDEX
    Explanations

    Latin words

    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_50_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
     hamming
    0.41
     הולנד
    0.41
    Accent
    0.37
    য়দ
    0.37
     Pren
    0.37
     आईडी
    0.36
    徊
    0.36
    Pren
    0.35
     Student
    0.35
    忍
    0.35
    POSITIVE LOGITS
     بدر
    0.42
     MO
    0.41
    ictionary
    0.39
    秪
    0.38
     Mo
    0.38
    ies
    0.37
     mo
    0.37
    apr
    0.36
     br
    0.36
    ense
    0.36
    Activations Density 0.000%

    No Known Activations