© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80433
    Prev
    Next
    INDEX
    Explanations

    sexual abuse and exploitation

    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_31_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
     (`
    0.39
     (**
    0.36
     entanto
    0.35
     однако
    0.35
    却
    0.34
     tent
    0.34
    .${
    0.33
    otyp
    0.32
     zunächst
    0.32
    ighters
    0.32
    POSITIVE LOGITS
    łę
    0.38
     steve
    0.37
     EVEN
    0.34
    এশিয়া
    0.34
    Ꮃ
    0.34
    ជ្
    0.33
     مهما
    0.33
    짙
    0.33
    Ꮓ
    0.33
    zyc
    0.32
    Activations Density 0.058%

    No Known Activations