© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198000
    Prev
    Next
    INDEX
    Explanations

    precipitate formed

    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_27_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
    ăr
    0.38
    OrderID
    0.38
    ल्यावर
    0.38
    alls
    0.37
    ორციელ
    0.36
    MinWidth
    0.35
    🅘
    0.35
     සිට
    0.35
    啬
    0.35
     величи
    0.35
    POSITIVE LOGITS
    こ
    0.43
    小物
    0.41
     Sesame
    0.39
     innocuous
    0.38
     occupation
    0.36
     consulte
    0.36
     食
    0.36
     oce
    0.36
    ository
    0.36
     incongru
    0.36
    Activations Density 0.005%

    No Known Activations