© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61446
    Prev
    Next
    INDEX
    Explanations

    lived experience

    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_11_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
     ‘’
    0.39
    ‘’
    0.38
    ঁ
    0.36
    怸
    0.36
     Emperors
    0.35
     ‘‘
    0.35
    ﹙
    0.34
     現在
    0.34
    如果没有
    0.34
     зокрема
    0.34
    POSITIVE LOGITS
    u
    0.43
    r
    0.40
    वरून
    0.39
    k
    0.38
    uus
    0.37
    i
    0.37
    greet
    0.36
    Q
    0.36
    User
    0.36
    Ster
    0.36
    Activations Density 0.009%

    No Known Activations