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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236843
    Prev
    Next
    INDEX
    Explanations

    sentence ending 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_25_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
     weekly
    0.36
     investig
    0.35
     consultative
    0.35
     jurisdictions
    0.35
     investigate
    0.35
    ক্ষেত্র
    0.34
    <sup>
    0.33
     cuch
    0.33
    RESOL
    0.33
     ->
    0.32
    POSITIVE LOGITS
     созда
    0.42
     이름
    0.41
    bik
    0.40
     století
    0.38
     буквы
    0.38
     बेटियों
    0.37
     তোমাকে
    0.37
    fik
    0.37
    utacji
    0.36
     закреп
    0.36
    Activations Density 0.005%

    No Known Activations