© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195393
    Prev
    Next
    INDEX
    Explanations

    harmful behavior normalization

    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_27_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
     माँग
    0.38
     management
    0.38
    regex
    0.35
     Magazines
    0.35
     cnt
    0.34
    Ark
    0.34
     Melon
    0.34
    규
    0.33
     magazine
    0.33
     Ark
    0.33
    POSITIVE LOGITS
     composta
    0.41
    olphe
    0.40
    ϟ
    0.39
     +=
    0.38
     ശു
    0.38
     snelheid
    0.38
    Ꮨ
    0.38
    伸ば
    0.37
     cloudinary
    0.37
    вропей
    0.37
    Activations Density 0.050%

    No Known Activations