© 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. 215741
    Prev
    Next
    INDEX
    Explanations

    It followed by a verb or adjective

    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
    在高
    0.38
    高质量
    0.37
    মাণ
    0.37
     perfected
    0.36
    誢
    0.36
    高性能
    0.36
    诰
    0.36
     Джа
    0.34
     lush
    0.34
     Whose
    0.34
    POSITIVE LOGITS
     सबकुछ
    0.41
     defences
    0.38
    凳
    0.36
    netbeans
    0.36
     သည်
    0.36
     కొంత
    0.36
    segn
    0.35
    бата
    0.35
     even
    0.35
    甚至是
    0.35
    Activations Density 0.003%

    No Known Activations