© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33199
    Prev
    Next
    INDEX
    Explanations

    \infty bound

    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
     respectively
    0.35
    分别为
    0.35
    ভেন
    0.34
     treas
    0.34
    uncertain
    0.33
    rophages
    0.33
    izos
    0.32
    匼
    0.32
    다라고
    0.32
     unspecified
    0.31
    POSITIVE LOGITS
     lét
    0.38
     Kirst
    0.38
    іль
    0.38
     ਕੁ
    0.38
     علت
    0.38
     دفع
    0.37
     hau
    0.37
     plume
    0.37
     बढ़
    0.36
     እንቅ
    0.36
    Activations Density 0.000%

    No Known Activations