© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    column names

    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
    س
    2.61
    .*/
    2.60
    😠
    2.53
     Дело
    2.50
    ಸ್ತ
    2.45
    पत्र
    2.43
    
    2.39
     calcareous
    2.37
    __________
    2.36
    ल
    2.36
    POSITIVE LOGITS
    as
    2.85
    ના
    2.55
    <bos>
    2.54
     macam
    2.46
    ழ்
    2.34
    ভাবে
    2.29
     suivant
    2.28
    দিষ্ট
    2.25
    ность
    2.23
    suivant
    2.22
    Activations Density 0.026%

    No Known Activations