© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76297
    Prev
    Next
    INDEX
    Explanations

    static variable declarations

    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
    Herd
    0.37
     Đức
    0.36
    )^{
    0.35
     नोन
    0.35
    arschijnlijk
    0.35
     deja
    0.34
     displace
    0.34
     casco
    0.34
     späteren
    0.34
     disjoint
    0.34
    POSITIVE LOGITS
    努力
    0.42
     ستر
    0.41
    laug
    0.40
    霖
    0.39
    রাষ্ট্রমন্ত্রী
    0.38
    REQUEST
    0.38
    模様
    0.37
     became
    0.35
     bedeut
    0.35
    內的
    0.35
    Activations Density 0.000%

    No Known Activations