© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3363
    Prev
    Next
    INDEX
    Explanations

    bright + color

    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
    ỷ
    1.00
     प्रबल
    0.88
    Markov
    0.83
    HING
    0.82
     priori
    0.80
    ्रेडिट
    0.80
    쯔
    0.79
    蒾
    0.79
    瘩
    0.77
     Trunk
    0.77
    POSITIVE LOGITS
    ва
    0.87
     hues
    0.84
    blau
    0.81
     colours
    0.78
    kter
    0.77
    blonde
    0.75
     inauguration
    0.75
    parseFloat
    0.74
    到处
    0.74
    tní
    0.74
    Activations Density 0.056%

    No Known Activations