© 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. 7735
    Prev
    Next
    INDEX
    Explanations

    coffee or tea

    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
    mati
    0.87
    ened
    0.84
    ונה
    0.82
    할
    0.81
    ening
    0.81
    INA
    0.80
    го
    0.80
     canes
    0.79
     KeyError
    0.78
    Пло
    0.77
    POSITIVE LOGITS
    currentChar
    0.97
    ch
    0.93
     resultSet
    0.89
    isInt
    0.88
     срок
    0.82
     brink
    0.82
     textField
    0.82
     ℝ
    0.81
    Ako
    0.80
     anum
    0.80
    Activations Density 0.011%

    No Known Activations