© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    to + action/purpose

    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
    
    0.67
    
    0.64
     vestiges
    0.63
    ない
    0.63
     gewoon
    0.60
    ‌ನ
    0.58
    一方で
    0.57
    𝔹
    0.56
    sofar
    0.56
     ͡
    0.56
    POSITIVE LOGITS
    Џ
    0.62
    carte
    0.59
    પ્ર
    0.58
    Вот
    0.56
    鐘
    0.55
    িট
    0.55
    钟
    0.55
    মত
    0.55
    ight
    0.53
    ности
    0.51
    Activations Density 0.072%

    No Known Activations