© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49309
    Prev
    Next
    INDEX
    Explanations

    different languages

    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_55_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
    Thus
    0.41
    Areas
    0.41
    thus
    0.40
     Thus
    0.40
    cy
    0.38
     erect
    0.37
     stille
    0.37
    く
    0.37
    ocon
    0.36
    Ни
    0.36
    POSITIVE LOGITS
     ಅವರಿಗೆ
    0.43
     hier
    0.40
     mentre
    0.39
    当时
    0.38
     ಅದನ್ನು
    0.38
     त्यावेळी
    0.38
     daar
    0.38
    ただ
    0.38
     sementara
    0.38
    さすが
    0.37
    Activations Density 0.000%

    No Known Activations