© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28037
    Prev
    Next
    INDEX
    Explanations

    suicide prevention

    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_40_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
     লক্ষ
    0.43
    тике
    0.42
    惱
    0.42
    thorace
    0.40
     ప్రే
    0.39
    Dependent
    0.38
    OLDS
    0.38
     bombing
    0.37
     Bibliothèque
    0.37
    折
    0.36
    POSITIVE LOGITS
    born
    0.39
    pd
    0.38
     born
    0.35
    aceous
    0.35
    鎌
    0.34
    నికి
    0.34
    uuid
    0.33
     diabet
    0.33
    gen
    0.33
    osaur
    0.33
    Activations Density 0.002%

    No Known Activations