© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11166
    Prev
    Next
    INDEX
    Explanations

    motion or judgment

    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_13_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
    滞
    0.57
    تين
    0.53
    কানিক্যাল
    0.47
    Cay
    0.46
     â
    0.44
    Buf
    0.43
    Wallace
    0.43
    製造
    0.43
    क्लेव
    0.43
    大会
    0.42
    POSITIVE LOGITS
    iny
    0.57
     ρ
    0.54
    েরিক
    0.54
     им
    0.52
     х
    0.51
     hern
    0.51
    INY
    0.50
    andha
    0.50
    pergillus
    0.50
     посредством
    0.50
    Activations Density 0.003%

    No Known Activations