© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    Ari, Ariane, election, Germany

    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_40_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
     Woolf
    0.38
     verv
    0.37
    架
    0.36
    lint
    0.35
    ª
    0.35
     Mant
    0.35
    GEST
    0.35
     উন্ম
    0.35
    ผ้า
    0.35
    金
    0.35
    POSITIVE LOGITS
    Ari
    0.47
     Ari
    0.44
     disg
    0.41
    夕
    0.40
    Germany
    0.39
     নির্বাচন
    0.39
     Dangerous
    0.38
    ꯟ
    0.38
     হুঁশিয়ার
    0.38
     posisi
    0.37
    Activations Density 0.016%

    No Known Activations