© 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. 11614
    Prev
    Next
    INDEX
    Explanations

    sensitivity / sensitive

    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
    рования
    0.41
    CLS
    0.36
     Mif
    0.36
     Scheduling
    0.36
    ೪
    0.36
     cuidar
    0.36
     Setting
    0.35
    ->_
    0.35
    Swiss
    0.35
    IEF
    0.35
    POSITIVE LOGITS
     sensitivity
    0.83
     Sensitivity
    0.74
    sensitivity
    0.71
    Sensitivity
    0.70
     sensibilidad
    0.69
     sensibilité
    0.59
     حساس
    0.59
     чувстви
    0.59
     sensitivities
    0.58
    sensitive
    0.55
    Activations Density 0.068%

    No Known Activations