© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38742
    Prev
    Next
    INDEX
    Explanations

    foreign words and sounds

    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_3_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
    >
    0.87
    ’।
    0.80
    ’,
    0.80
    ^{*},
    0.79
    ,’
    0.76
     kttt
    0.75
    ו
    0.75
    (),
    0.74
    ></
    0.73
    ၊
    0.72
    POSITIVE LOGITS
    ai
    0.89
    l
    0.79
     sauté
    0.75
     was
    0.72
    lL
    0.72
    0.71
    ah
    0.70
    patial
    0.69
    was
    0.69
     nation
    0.68
    Activations Density 0.001%

    No Known Activations