© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    government ministries and officials

    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
    wdriver
    0.75
    ꒦
    0.64
    त्मक
    0.62
     towing
    0.62
    ceptions
    0.62
     maxLength
    0.61
     urbana
    0.59
     unus
    0.59
     intArray
    0.58
    ached
    0.57
    POSITIVE LOGITS
     pijn
    0.74
     ministers
    0.61
    य
    0.60
     vlá
    0.55
     मंत्री
    0.55
     Ministers
    0.54
    präsident
    0.53
     Ꭰ
    0.53
    FV
    0.53
    irman
    0.53
    Activations Density 0.031%

    No Known Activations