© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88117
    Prev
    Next
    INDEX
    Explanations

    code obfuscation and code point

    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_3_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
    та
    0.76
    的
    0.65
    น
    0.64
    <0x0D>
    0.63
    ثل
    0.62
    ش
    0.60
    ুরা
    0.58
    ્ય
    0.57
    ن
    0.56
    ant
    0.55
    POSITIVE LOGITS
    0.59
     می‌کنند
    0.59
     સમગ્ર
    0.59
     I
    0.57
     testimonial
    0.56
     Yemen
    0.55
    岨
    0.55
     WALTER
    0.55
     ഓരോ
    0.54
    gll
    0.54
    Activations Density 0.001%

    No Known Activations