© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64151
    Prev
    Next
    INDEX
    Explanations

    State

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Hudson
    0.56
     hudson
    0.50
    Hudson
    0.47
     HUD
    0.46
     হাইড্রোজেন
    0.44
     harbor
    0.42
     京
    0.42
    리카
    0.42
    hydrogen
    0.41
    Hud
    0.40
    POSITIVE LOGITS
    Empire
    0.48
     Empire
    0.47
     числен
    0.42
     импе
    0.42
     шум
    0.39
     empire
    0.39
     краї
    0.39
     noisy
    0.38
     ใบ
    0.37
    αρ
    0.37
    Activations Density 0.000%

    No Known Activations