© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5411
    Prev
    Next
    INDEX
    Explanations

    cosmic, contemporary, beyond

    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
    ação
    0.54
    我看
    0.54
    ged
    0.54
    o
    0.53
    cular
    0.52
    nya
    0.52
    áč
    0.52
    iem
    0.52
    ah
    0.51
    am
    0.51
    POSITIVE LOGITS
     azimuthal
    0.58
     terpenes
    0.57
    ций
    0.56
    imposed
    0.56
    ق
    0.55
    טו
    0.54
     тыс
    0.54
     affirmat
    0.52
    涳
    0.52
    पंजाब
    0.52
    Activations Density 0.027%

    No Known Activations