© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10599
    Prev
    Next
    INDEX
    Explanations

    specific entities, events, or codes

    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_40_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
    cipe
    0.42
    ろしく
    0.37
     меню
    0.37
     Menu
    0.37
    ⁿ
    0.36
    nivers
    0.36
     except
    0.36
     km
    0.36
     EXCEPT
    0.35
     Story
    0.35
    POSITIVE LOGITS
    ဖြစ်
    0.44
    കേ
    0.40
    ങ്കി
    0.38
    চিতের
    0.38
    unzione
    0.37
    Ἠ
    0.36
    ……”
    0.36
    अमेरिकी
    0.36
     قرآن
    0.35
    ោម
    0.35
    Activations Density 0.050%

    No Known Activations