© 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. 7818
    Prev
    Next
    INDEX
    Explanations

    A17 Bionic

    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
     recorrido
    2.33
     обраща
    2.26
    ្នែក
    2.23
     NoSuch
    2.18
    ই
    2.16
     sight
    2.14
    ума
    2.13
     sot
    2.06
    ್ಯ
    2.06
     downlink
    2.05
    POSITIVE LOGITS
    т
    3.33
     awfully
    2.71
    leme
    2.57
    i
    2.55
    gli
    2.54
    fool
    2.48
    lem
    2.43
    tin
    2.43
    tul
    2.41
    slightly
    2.39
    Activations Density 0.006%

    No Known Activations