© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63445
    Prev
    Next
    INDEX
    Explanations

    Atlas related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     mother
    1.41
     motherboard
    1.41
    mother
    1.39
    Mother
    1.37
     moeder
    1.34
     Mother
    1.31
    母
    1.27
     madre
    1.22
     مادر
    1.18
     mãe
    1.16
    POSITIVE LOGITS
     technique
    0.39
     flog
    0.38
     Ads
    0.37
     fieldContext
    0.35
    祎
    0.35
    テク
    0.35
    ференциа
    0.33
    ongo
    0.33
     swag
    0.33
    gegen
    0.33
    Activations Density 0.001%

    No Known Activations