© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106828
    Prev
    Next
    INDEX
    Explanations

    dangerousness, violence, risks

    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_1_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
    ↵
    1.27
     on
    1.06
    l
    1.05
     to
    1.04
    ้ำ
    1.03
    ल
    0.91
     at
    0.91
    рование
    0.90
    ění
    0.90
    মেন্ট
    0.89
    POSITIVE LOGITS
    in
    1.20
    ing
    1.20
    다
    1.20
    {
    1.17
    ır
    1.16
    am
    1.13
    ة
    1.13
    ود
    1.11
    ле
    1.08
    та
    1.06
    Activations Density 0.000%

    No Known Activations