© 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. 32718
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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
    icherweise
    0.38
     தாக்க
    0.38
     mức
    0.36
    ichten
    0.35
    町の
    0.35
     ಸೂ
    0.35
    派出
    0.35
    釟
    0.35
    сього
    0.34
    欢乐
    0.34
    POSITIVE LOGITS
     इसीलिए
    0.84
    hence
    0.80
     hence
    0.79
     dlatego
    0.77
    Hence
    0.76
     why
    0.75
     Hence
    0.75
     Deshalb
    0.71
     deshalb
    0.70
     అందుకే
    0.69
    Activations Density 0.045%

    No Known Activations