© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36848
    Prev
    Next
    INDEX
    Explanations

    instructions

    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_50_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
     cheated
    0.46
    ктери
    0.44
     H
    0.43
     cheat
    0.42
     scriptlevel
    0.40
     הה
    0.40
    cheat
    0.39
    酞
    0.39
     cdr
    0.39
     फ्लैट
    0.37
    POSITIVE LOGITS
     Lorenz
    0.44
     hyd
    0.44
    Day
    0.42
    zu
    0.42
    Ban
    0.42
     qt
    0.41
     Quinn
    0.41
    Zu
    0.41
    lul
    0.38
    Zen
    0.38
    Activations Density 0.047%

    No Known Activations