© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198481
    Prev
    Next
    INDEX
    Explanations

    impress

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    fäh
    0.42
    gives
    0.41
     Gippsland
    0.41
    Curt
    0.40
    }}^{-
    0.40
    גי
    0.38
    PhysicalDevice
    0.38
    Single
    0.37
     Curt
    0.37
    ֿ
    0.37
    POSITIVE LOGITS
     impress
    0.61
     impressed
    0.61
     impres
    0.54
     impressive
    0.47
     impressing
    0.47
     impresses
    0.43
     beeindruck
    0.41
    Impress
    0.41
    йо
    0.41
    impress
    0.39
    Activations Density 0.011%

    No Known Activations