© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233022
    Prev
    Next
    INDEX
    Explanations

    sexual assault survivors

    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_32_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
     మరియు
    0.28
     Interests
    0.28
     пункт
    0.28
    ̼
    0.27
     максима
    0.27
     flanges
    0.27
    犁
    0.27
     приня
    0.26
     микро
    0.26
     максимально
    0.26
    POSITIVE LOGITS
    wość
    0.33
    Douglas
    0.33
    IONAL
    0.31
    🈚
    0.31
    ITIONAL
    0.31
    Congressional
    0.31
     congressional
    0.31
    interactive
    0.30
     transatlantic
    0.30
     პირადი
    0.30
    Activations Density 0.002%

    No Known Activations