© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3139
    Prev
    Next
    INDEX
    Explanations

    maximum length and value

    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_5_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
    गेटिव
    0.70
    кість
    0.70
    isinde
    0.64
    ্যান
    0.63
    borne
    0.63
     całym
    0.61
    r
    0.61
    ıları
    0.61
    egrave
    0.61
    ษา
    0.59
    POSITIVE LOGITS
    ња
    0.87
    िमम
    0.85
     roc
    0.76
     hangout
    0.76
    aching
    0.74
    %>%
    0.73
    editText
    0.72
    prosperity
    0.71
     installments
    0.70
     enkelt
    0.70
    Activations Density 0.276%

    No Known Activations