© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2415
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cay
    0.55
    Mc
    0.53
    }/
    0.53
    elm
    0.53
    BA
    0.51
                      
    0.50
    akin
    0.50
     carin
    0.49
    <0xE2>
    0.49
    Welcome
    0.49
    POSITIVE LOGITS
     मैथ्स
    0.71
    শিকান্ত
    0.63
     Diện
    0.61
     Մ
    0.61
     Když
    0.60
     ভারতীয়রা
    0.59
    dött
    0.59
    rawberry
    0.59
    ructures
    0.59
    <0xB5>
    0.58
    Activations Density 0.006%

    No Known Activations