© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5703
    Prev
    Next
    INDEX
    Explanations

    support

    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
    и
    3.46
    ти
    3.10
    ak
    2.78
    it
    2.71
    স
    2.69
    ஆர்
    2.48
    াইট
    2.47
    ид
    2.42
     arrivée
    2.41
    ో
    2.41
    POSITIVE LOGITS
     принятия
    3.12
    
    2.76
    """"""""
    2.74
    LessThan
    2.64
     getSupport
    2.61
     inversely
    2.60
    ㅄ
    2.48
     Electrons
    2.47
     Miocene
    2.45
    less
    2.43
    Activations Density 0.007%

    No Known Activations