© 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. 40376
    Prev
    Next
    INDEX
    Explanations

    impeachment trial proceedings

    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
     Indien
    0.66
     is
    0.59
    フランス
    0.58
     समुद्र
    0.57
    ning
    0.57
    ਨ
    0.55
     India
    0.54
     कौन
    0.54
    是
    0.54
    ny
    0.54
    POSITIVE LOGITS
    俐
    0.65
     mildly
    0.59
    ורים
    0.58
    یتی
    0.57
    JKL
    0.56
    StaffID
    0.56
    юще
    0.55
    MNOP
    0.55
    тт
    0.55
    ння
    0.54
    Activations Density 0.002%

    No Known Activations