© 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. 57437
    Prev
    Next
    INDEX
    Explanations

    gov, officials, liberal, conservative

    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
    ба
    0.68
     Were
    0.61
     January
    0.59
    ذف
    0.58
     гром
    0.57
    н
    0.57
    tained
    0.57
    ンの
    0.56
    τών
    0.56
     Notify
    0.55
    POSITIVE LOGITS
     coisas
    0.68
     cosas
    0.66
    는
    0.66
     camiseta
    0.62
     chromosomes
    0.61
     বর্ণের
    0.59
     واحدة
    0.57
     aplik
    0.56
    是可以
    0.56
     camels
    0.55
    Activations Density 0.007%

    No Known Activations