© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198443
    Prev
    Next
    INDEX
    Explanations

    results.paga

    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_12_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
     creates
    0.57
    ला
    0.54
     создавать
    0.54
     imitating
    0.52
     renew
    0.51
     unified
    0.50
    ℎ
    0.50
     accelerated
    0.50
     renewing
    0.50
    h
    0.50
    POSITIVE LOGITS
     കാഴ്ച
    0.61
    朝鲜
    0.55
    </em>
    0.54
    ి
    0.52
    辂
    0.52
     Agricultura
    0.51
     Malhotra
    0.51
     Platforms
    0.51
     sådan
    0.51
     McNamara
    0.51
    Activations Density 0.000%

    No Known Activations