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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198999
    Prev
    Next
    INDEX
    Explanations

    North

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     C
    0.44
    ヨーク
    0.42
    yon
    0.42
     ಗ್ರ
    0.41
     Montana
    0.40
    Montana
    0.40
     Yon
    0.40
    arness
    0.40
    mites
    0.39
     Conquer
    0.38
    POSITIVE LOGITS
     North
    0.50
    North
    0.49
    北
    0.48
     북
    0.42
     北
    0.38
    لا
    0.38
     dew
    0.38
    昔
    0.38
    Bubble
    0.37
     T
    0.37
    Activations Density 0.015%

    No Known Activations