© 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. 8628
    Prev
    Next
    INDEX
    Explanations

    1903

    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
     Далее
    2.51
     ï
    2.38
    इसके
    2.33
    يري
    2.30
     arbe
    2.29
    gı
    2.27
    arthed
    2.26
     insurg
    2.24
     Além
    2.23
    मुझे
    2.16
    POSITIVE LOGITS
    窿
    2.52
    ya
    2.23
     borderRadius
    2.23
     supposing
    2.21
    NSMakeRange
    2.20
     pcs
    2.20
    hairs
    2.18
    tear
    2.15
    з
    2.14
    LinkedList
    2.14
    Activations Density 0.002%

    No Known Activations