© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 422
    Prev
    Next
    INDEX
    Explanations

    что лучше?

    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_38_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
     學
    0.58
     hecha
    0.51
    ajouter
    0.51
     gols
    0.49
    Για
    0.49
     Metode
    0.49
    قیه
    0.49
    melee
    0.48
     Ανακτήθηκε
    0.48
    र्में
    0.47
    POSITIVE LOGITS
     при
    0.61
     за
    0.60
     крити
    0.55
     у
    0.54
     непро
    0.54
     в
    0.54
     про
    0.54
     ма
    0.54
     описа
    0.54
     знако
    0.54
    Activations Density 0.092%

    No Known Activations