© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198140
    Prev
    Next
    INDEX
    Explanations

    a

    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
     aprendido
    0.44
     digitization
    0.40
    lceil
    0.39
     erud
    0.39
     士
    0.39
     नैतिकता
    0.39
     digitalisation
    0.38
     adjoint
    0.38
    сс
    0.38
     master
    0.37
    POSITIVE LOGITS
    factor
    0.42
    Factor
    0.40
     charter
    0.40
    Rec
    0.39
    FACTOR
    0.38
     factor
    0.37
    findall
    0.37
    バ
    0.37
    方向
    0.36
     stockholder
    0.36
    Activations Density 0.001%

    No Known Activations