© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69129
    Prev
    Next
    INDEX
    Explanations

    currencies and amounts

    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_46_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
     τά
    0.41
    eping
    0.35
     US
    0.34
     Estates
    0.34
    カロ
    0.33
    ļ
    0.32
     имуще
    0.32
    oid
    0.32
     estates
    0.32
    bery
    0.32
    POSITIVE LOGITS
    烣
    0.44
     Qg
    0.41
    쉬
    0.41
     eigenfunctions
    0.39
     Fuente
    0.39
     cleansing
    0.39
    owneri
    0.39
     hypers
    0.38
    ოვნ
    0.38
    backgroundImage
    0.37
    Activations Density 0.002%

    No Known Activations