© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51504
    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_31_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
    Denn
    0.39
    これから
    0.37
     ~
    0.37
     cracks
    0.36
     '^
    0.36
     {
    0.34
    <0xDB>
    0.33
     क्वेश्चंस
    0.32
    ឡ
    0.32
    נס
    0.32
    POSITIVE LOGITS
     дол
    0.43
     hassle
    0.43
     해야
    0.42
     hassles
    0.40
    Drawable
    0.40
     usados
    0.39
     teclas
    0.38
     ব্যবহৃত
    0.37
     bother
    0.37
     actes
    0.37
    Activations Density 0.006%

    No Known Activations