© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123324
    Prev
    Next
    INDEX
    Explanations

    normalization of harmful behaviors

    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_37_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
     sufrimiento
    0.36
     Habits
    0.36
     habit
    0.36
     Hàm
    0.35
     Habit
    0.35
    >${
    0.34
    UniqueID
    0.34
     Vitt
    0.34
     हादसा
    0.34
    דיו
    0.34
    POSITIVE LOGITS
     bounce
    0.41
     Gunnar
    0.40
    抢
    0.39
    られる
    0.39
     enqueue
    0.38
     affording
    0.38
     PAX
    0.37
     invade
    0.37
    nights
    0.37
    nous
    0.37
    Activations Density 0.030%

    No Known Activations