© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6689
    Prev
    Next
    INDEX
    Explanations

    import android.view.View

    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_39_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
     resurrection
    0.47
     mobilization
    0.44
    犬
    0.42
     लॉस
    0.41
    andal
    0.39
     করিলেন
    0.38
     docked
    0.38
    canoe
    0.38
    擡
    0.38
     docking
    0.38
    POSITIVE LOGITS
    CSS
    0.45
    Thread
    0.44
     Hemisphere
    0.41
     CSS
    0.40
    σι
    0.38
     CSI
    0.38
    си
    0.38
    ремя
    0.36
    Prima
    0.36
     pö
    0.36
    Activations Density 0.005%

    No Known Activations