© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    email subject starters

    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
    Ռ
    1.96
    খানেই
    1.95
     visor
    1.88
     nextline
    1.85
     solidification
    1.84
    сь
    1.83
     dez
    1.82
     tep
    1.81
     caring
    1.81
     gras
    1.77
    POSITIVE LOGITS
    о
    2.14
    ी
    2.13
    ി
    1.95
    radioButton
    1.88
    ../../
    1.87
    د
    1.87
    tareas
    1.87
    ळे
    1.87
    ANSWER
    1.85
    dard
    1.82
    Activations Density 0.010%

    No Known Activations