© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6946
    Prev
    Next
    INDEX
    Explanations

    prepositions before locations or events

    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
    en
    0.70
    กิจ
    0.66
    י
    0.62
     behalf
    0.60
    eniz
    0.58
    ни
    0.57
    ку
    0.57
    ially
    0.57
    ة
    0.57
    ת
    0.56
    POSITIVE LOGITS
    issauga
    0.70
     permeates
    0.69
    ྕ
    0.65
    詈
    0.64
     blamed
    0.64
    getData
    0.64
    膀
    0.62
     fullback
    0.62
    ঠিত
    0.62
    mainWindow
    0.61
    Activations Density 0.344%

    No Known Activations