© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210352
    Prev
    Next
    INDEX
    Explanations

    final event

    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_43_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
     decisive
    1.83
     decis
    1.59
     conclusive
    1.36
     definitive
    1.32
     decisively
    1.29
     निर्णायक
    1.29
    决
    1.15
     entscheid
    1.08
    決
    1.05
     deciding
    1.03
    POSITIVE LOGITS
    Embed
    0.41
    रव
    0.40
    poor
    0.39
    垍
    0.39
    Chel
    0.38
    匀
    0.38
    橦
    0.38
    ЕН
    0.38
    нуу
    0.38
    Met
    0.37
    Activations Density 0.011%

    No Known Activations