© 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. 4653
    Prev
    Next
    INDEX
    Explanations

    Chaturanga

    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
    ل
    2.58
     dispose
    2.31
     rezultat
    2.23
    ளில்
    2.23
    ()=>{
    2.11
    lact
    2.04
    𝘮
    2.02
     savent
    2.00
    ानों
    1.99
     HttpClient
    1.98
    POSITIVE LOGITS
    е
    2.88
    ки
    2.82
    й
    2.29
    an
    2.24
     glimps
    2.19
    ned
    2.08
    তা
    2.06
    ം
    2.05
    ীয়
    1.97
    }^{
    1.92
    Activations Density 0.002%

    No Known Activations