© 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. 42519
    Prev
    Next
    INDEX
    Explanations

    laser projections, party decorations

    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
    ル
    0.33
     privileges
    0.33
    emat
    0.31
    šení
    0.31
     specializing
    0.30
    েস
    0.30
    zenie
    0.30
    בר
    0.30
    ｽ
    0.29
    ერი
    0.29
    POSITIVE LOGITS
     posters
    0.45
     t
    0.39
     poster
    0.37
     Posters
    0.37
     पोस्टर
    0.33
     национа
    0.32
     ..."
    0.32
     націона
    0.31
     шесть
    0.30
    poster
    0.30
    Activations Density 0.001%

    No Known Activations