© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81582
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes or suffixes

    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_0_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
    ни
    1.72
    能
    1.55
    是
    1.50
    ↵↵
    1.38
    اني
    1.34
    న్లు
    1.30
    мана
    1.30
    ル
    1.27
    л
    1.27
    న్
    1.26
    POSITIVE LOGITS
    .
    1.95
     you
    1.69
    ties
    1.44
     with
    1.38
    9
    1.38
    _
    1.35
    5
    1.30
    you
    1.30
    ।
    1.30
     worded
    1.25
    Activations Density 0.000%

    No Known Activations