© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9916
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    ❤
    0.46
    砾
    0.46
    ❤❤
    0.46
     ❤
    0.43
    better
    0.43
     ♥
    0.42
    ompact
    0.41
    깎
    0.40
     better
    0.39
    ❤️
    0.39
    POSITIVE LOGITS
     See
    0.39
     Keen
    0.38
     Sep
    0.38
     Codes
    0.37
     Component
    0.36
     Summary
    0.36
     Arth
    0.35
    胞
    0.35
     Aye
    0.35
     Barnard
    0.35
    Activations Density 0.014%

    No Known Activations