© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87819
    Prev
    Next
    INDEX
    Explanations

    named capturing groups `(?P<name>...)`

    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_18_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
     verkauft
    0.55
    а
    0.52
     Finance
    0.52
    getragen
    0.51
    🍣
    0.51
     Unternehmens
    0.51
     škola
    0.50
    eyim
    0.49
     Lorsqu
    0.49
    satz
    0.48
    POSITIVE LOGITS
     obstruct
    0.47
     obstacles
    0.46
     عمد
    0.46
     obstacle
    0.45
     օ
    0.44
    VARCHAR
    0.44
     متع
    0.43
     cold
    0.43
     camel
    0.42
     व्यव
    0.42
    Activations Density 0.000%

    No Known Activations