© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209099
    Prev
    Next
    INDEX
    Explanations

    **brain** and **CNS**

    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_19_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
    second
    0.29
    increase
    0.28
    called
    0.28
    going
    0.26
    since
    0.26
    l
    0.26
    factors
    0.25
    Daisy
    0.25
    except
    0.25
     restart
    0.24
    POSITIVE LOGITS
    块
    0.25
     şə
    0.24
    塊
    0.24
     Đường
    0.23
    しないで
    0.23
    钏
    0.23
    湋
    0.23
    出
    0.23
    📪
    0.23
     ಸ್ನೇ
    0.23
    Activations Density 0.004%

    No Known Activations