© 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. 62756
    Prev
    Next
    INDEX
    Explanations

    NASA links

    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
     vliegt
    0.47
     سٹ
    0.41
    飞
    0.38
     Má
    0.38
    絶縁
    0.38
    ート
    0.37
     են
    0.37
     опу
    0.36
     genial
    0.36
    znej
    0.36
    POSITIVE LOGITS
    Junior
    0.43
     NATO
    0.39
    NATO
    0.39
    칭
    0.39
     Chakrab
    0.39
    nato
    0.38
    synchron
    0.38
     Nato
    0.38
    Term
    0.37
    Ta
    0.36
    Activations Density 0.001%

    No Known Activations