© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3649
    Prev
    Next
    INDEX
    Explanations

    memorial day

    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
    റേ
    0.82
    NUMX
    0.81
    rays
    0.78
    ن
    0.77
     tät
    0.75
    يا
    0.74
    ই
    0.73
     maison
    0.72
    ので
    0.72
    ainte
    0.71
    POSITIVE LOGITS
     memorials
    0.83
    dí
    0.82
    ς
    0.78
    managedbuild
    0.78
    तना
    0.75
    ↥
    0.75
     customtkinter
    0.74
    需
    0.74
               
    0.74
     ===============
    0.73
    Activations Density 0.050%

    No Known Activations