© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126430
    Prev
    Next
    INDEX
    Explanations

    federal power

    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_37_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
     결방
    0.36
    잉
    0.35
    अप्र
    0.35
     प्रीमियर
    0.35
     Polarization
    0.35
     gax
    0.35
     immédi
    0.34
     GPA
    0.34
     premiership
    0.34
    MessageNow
    0.33
    POSITIVE LOGITS
     powers
    0.43
    數
    0.42
    পেক্ষ
    0.39
    Powers
    0.39
    Viki
    0.39
     Anch
    0.37
     Vikings
    0.37
     carrying
    0.37
     رائ
    0.37
     stretch
    0.36
    Activations Density 0.002%

    No Known Activations