Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4079
    Prev
    Next
    INDEX
    Explanations

    solar masses

    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
    bericht
    1.65
    Muito
    1.64
     `${
    1.59
    st
    1.58
    sinatra
    1.55
     lyd
    1.55
     barro
    1.55
     पढ़ेंः
    1.55
    odnik
    1.54
    Maui
    1.53
    POSITIVE LOGITS
     После
    1.58
    u
    1.55
     ورو
    1.46
     VStack
    1.45
    lying
    1.42
    லிய
    1.40
    攘
    1.38
    uq
    1.38
    жение
    1.37
     Нет
    1.37
    Activations Density 0.001%

    No Known Activations