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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_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
     step
    0.87
     želite
    0.76
     Schritt
    0.75
     veulent
    0.74
     нужны
    0.74
     మరింత
    0.74
    皮
    0.73
     potranno
    0.73
     iremos
    0.73
    नी
    0.72
    POSITIVE LOGITS
    íf
    0.71
     टाइगर
    0.70
     magaz
    0.69
     experts
    0.68
    ꒱
    0.66
     descriptors
    0.66
    experts
    0.65
     judges
    0.65
    mangle
    0.64
     dfs
    0.63
    Activations Density 0.002%

    No Known Activations