© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    often [verb describing state]

    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
    }=\
    0.78
    es
    0.75
     deforestation
    0.73
    ი
    0.70
    ្យ
    0.70
     conceivable
    0.70
    ст
    0.68
    ा
    0.68
    UAGES
    0.68
    ی
    0.66
    POSITIVE LOGITS
    ਰ
    0.72
    ED
    0.71
     બધા
    0.70
    UM
    0.70
    ers
    0.69
    гра
    0.68
     dasar
    0.68
    у
    0.68
     apropi
    0.66
    ()=>{
    0.65
    Activations Density 0.143%

    No Known Activations