© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207323
    Prev
    Next
    INDEX
    Explanations

    Canadian politics

    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_56_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
    hana
    0.40
     bơm
    0.38
     partant
    0.38
    તિ
    0.37
    ቻ
    0.37
     Rosh
    0.37
     Mana
    0.37
    慣
    0.36
    שרה
    0.35
     mana
    0.35
    POSITIVE LOGITS
     Harper
    1.12
    Harper
    1.08
     Liberal
    1.07
     Liberals
    1.02
    Liberal
    0.97
    Justin
    0.93
     Justin
    0.90
    Liber
    0.74
     NDP
    0.70
    Tr
    0.70
    Activations Density 0.001%

    No Known Activations