© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245606
    Prev
    Next
    INDEX
    Explanations

    BIGRU algorithms

    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_11_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
     hund
    0.83
     halves
    0.81
     $/
    0.81
     melt
    0.81
     earthquake
    0.77
     NBA
    0.76
     litro
    0.76
     Natura
    0.75
     restrictions
    0.74
     rentable
    0.74
    POSITIVE LOGITS
     존재
    0.78
     присутствует
    0.73
    까지
    0.70
     결과
    0.69
    presence
    0.69
    ت
    0.68
    progress
    0.68
    สู่
    0.67
     ګرځ
    0.67
    ങ്ങ
    0.66
    Activations Density 0.000%

    No Known Activations