© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41513
    Prev
    Next
    INDEX
    Explanations

    Child Sexual Abuse Material (CSAM)

    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_3_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
    á
    0.88
     souci
    0.77
    o
    0.74
    hão
    0.72
     вот
    0.71
    al
    0.68
    ción
    0.68
     проек
    0.66
    のための
    0.66
    h
    0.66
    POSITIVE LOGITS
    ت
    1.20
    т
    0.91
    ล
    0.85
    त
    0.81
    ICK
    0.79
    る
    0.75
    י
    0.75
    תה
    0.73
    توى
    0.72
    ل
    0.72
    Activations Density 0.002%

    No Known Activations