© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59075
    Prev
    Next
    INDEX
    Explanations

    law enforcement agencies

    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_2_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
    ні
    1.86
    ро
    1.76
    ری
    1.72
    ك
    1.66
    os
    1.61
    ма
    1.54
    ren
    1.49
    ре
    1.46
    ای
    1.38
    𝘱
    1.38
    POSITIVE LOGITS
    -
    1.65
    ר
    1.50
     haben
    1.27
    ’
    1.23
     reorgan
    1.18
                  
    1.16
    (
    1.16
     HAS
    1.15
    하는
    1.13
     (
    1.13
    Activations Density 0.000%

    No Known Activations