© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38397
    Prev
    Next
    INDEX
    Explanations

    government policy decisions and implementation

    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
     د
    0.59
    inspiring
    0.59
    دهای
    0.59
    ές
    0.59
    λογία
    0.58
     알려
    0.55
    𝗺
    0.54
    𝗱
    0.54
    to
    0.53
    лся
    0.53
    POSITIVE LOGITS
     Aplic
    0.60
     واي
    0.59
     Quando
    0.59
     Pentru
    0.59
     quando
    0.58
     qualidade
    0.57
     aumenta
    0.57
     fiecare
    0.57
    </h2>
    0.57
     Helvetica
    0.57
    Activations Density 0.002%

    No Known Activations