© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 148533
    Prev
    Next
    INDEX
    Explanations

    SSIS Package creation

    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
     superfici
    0.49
     Flächen
    0.48
     소프트
    0.48
     Surfaces
    0.48
     permukaan
    0.47
    塑料
    0.46
     superfície
    0.46
    씰
    0.46
    plastics
    0.46
     plástico
    0.46
    POSITIVE LOGITS
    schr
    0.57
    bajo
    0.47
    ut
    0.47
     tunes
    0.46
    D
    0.46
     patterns
    0.44
     activities
    0.43
     indifferent
    0.43
     indifference
    0.42
    隨著
    0.42
    Activations Density 0.000%

    No Known Activations