© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5948
    Prev
    Next
    INDEX
    Explanations

    ```xml and svg tags

    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
    ও
    2.49
    м
    2.38
     установлено
    2.31
     parasite
    2.25
    νά
    2.22
    ك
    2.20
    ik
    2.18
    ıp
    2.18
    ιών
    2.16
     infancia
    2.16
    POSITIVE LOGITS
     errMsg
    2.83
     tbsp
    2.65
    ć
    2.60
     Dateien
    2.59
     massive
    2.59
    ต์
    2.55
    tomato
    2.50
     Riemannian
    2.50
    sprintf
    2.48
    asible
    2.44
    Activations Density 0.011%

    No Known Activations