© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198770
    Prev
    Next
    INDEX
    Explanations

    browser support

    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
    ‌ల
    0.38
     reper
    0.38
    Bottom
    0.35
    len
    0.34
     resist
    0.34
    кость
    0.34
    \{-\
    0.33
    乡
    0.33
     genie
    0.32
     IOS
    0.32
    POSITIVE LOGITS
     बसी
    0.44
    撇
    0.43
     준
    0.41
     ronde
    0.40
     semper
    0.39
    滖
    0.38
     evo
    0.38
    嚟
    0.38
     мони
    0.38
     kazi
    0.38
    Activations Density 0.000%

    No Known Activations