© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165402
    Prev
    Next
    INDEX
    Explanations

    understand

    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_13_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
     وجود
    0.52
    protein
    0.50
    evin
    0.50
    comfort
    0.49
    ዖ
    0.48
     avanç
    0.48
     avanc
    0.47
    ᅨ
    0.47
    μί
    0.46
    demir
    0.46
    POSITIVE LOGITS
     October
    0.54
     McDonalds
    0.53
     rd
    0.51
    ありがとうございました
    0.50
    മാനം
    0.50
    間の
    0.50
     tanggal
    0.49
    udel
    0.49
     February
    0.48
     bhith
    0.48
    Activations Density 0.014%

    No Known Activations