© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59303
    Prev
    Next
    INDEX
    Explanations

    Pre-Raphaelite watercolor paintings

    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_2_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
    s
    1.66
    d
    1.41
    c
    1.41
    la
    1.35
    x
    1.34
    ды
    1.30
    る
    1.29
    3
    1.25
    w
    1.23
    ee
    1.21
    POSITIVE LOGITS
    IT
    1.14
    ਰ
    1.11
     monarchy
    1.08
    ン
    1.05
     oblik
    1.02
    क
    1.02
     hyphen
    1.01
     It
    1.00
     korte
    1.00
     fale
    1.00
    Activations Density 0.001%

    No Known Activations