© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212085
    Prev
    Next
    INDEX
    Explanations

    weather fronts and systems

    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_19_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
    かう
    0.43
    섀
    0.39
    䒩
    0.39
     могат
    0.39
     Virol
    0.39
     пау
    0.38
    也可
    0.38
    かわ
    0.38
     Flächen
    0.38
     Franks
    0.38
    POSITIVE LOGITS
    𝒕
    0.49
    𝑰
    0.48
    population
    0.48
    phan
    0.47
     judgmental
    0.47
     region
    0.47
     dangerously
    0.47
    各位同學
    0.47
     makanan
    0.46
     challenger
    0.46
    Activations Density 0.000%

    No Known Activations