© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214796
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_50_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
    ২৩
    1.34
     ২৩
    1.22
     XXIII
    0.88
    <unused23>
    0.75
     Twenty
    0.69
     twenty
    0.61
     २
    0.61
    Twenty
    0.58
     двадцать
    0.54
     ۲
    0.50
    POSITIVE LOGITS
    固有
    0.45
    noindent
    0.42
    壺
    0.40
    imek
    0.40
    <unused5>
    0.40
    TakeVideo
    0.39
    <unused32>
    0.37
    ylabel
    0.37
    மக
    0.37
    壷
    0.37
    Activations Density 0.012%

    No Known Activations