© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59771
    Prev
    Next
    INDEX
    Explanations

    international words and punctuation

    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
    ?
    1.12
     a
    1.00
    }$.
    0.98
    ,
    0.97
    し
    0.94
    り
    0.94
    ari
    0.92
    د
    0.92
    ä
    0.88
    !
    0.87
    POSITIVE LOGITS
    ות
    1.07
    ’
    1.01
    ’)
    0.91
    지
    0.89
    র
    0.88
    are
    0.86
    ın
    0.85
     for
    0.82
    ти
    0.81
     They
    0.79
    Activations Density 0.000%

    No Known Activations