© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8424
    Prev
    Next
    INDEX
    Explanations

    bubble tea shops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ت
    2.76
    ️
    2.72
     incidentally
    2.51
     й
    2.47
     injurious
    2.40
    o
    2.38
    sb
    2.32
    iest
    2.29
    要去
    2.27
    옛
    2.24
    POSITIVE LOGITS
    ENGTH
    2.48
     ид
    2.45
     خیال
    2.45
     yako
    2.43
    üman
    2.42
     adequada
    2.42
    गर्
    2.41
    ഹി
    2.41
     njima
    2.40
     высокую
    2.36
    Activations Density 0.000%

    No Known Activations