© 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. 18059
    Prev
    Next
    INDEX
    Explanations

    sexual assault

    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
    ,+
    0.40
    marginLeft
    0.38
    Нет
    0.36
    =+
    0.36
     Нет
    0.36
    emorrh
    0.36
     actitudes
    0.36
    곱
    0.35
    NING
    0.35
     profesores
    0.35
    POSITIVE LOGITS
     сило
    0.41
     Testing
    0.39
     бы
    0.39
     Khim
    0.39
    Testing
    0.39
     лиц
    0.39
     Pats
    0.38
     दाखल
    0.37
     тестирование
    0.36
    implies
    0.36
    Activations Density 0.012%

    No Known Activations