© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178439
    Prev
    Next
    INDEX
    Explanations

    Lady

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     slic
    0.41
    }`))
    0.38
     amounted
    0.38
     kisses
    0.37
    cje
    0.37
     indented
    0.37
     راحت
    0.37
    ៀ
    0.37
    缉
    0.37
     slice
    0.36
    POSITIVE LOGITS
     ہار
    0.40
    roup
    0.40
    ermi
    0.40
     Rutherford
    0.37
    石油
    0.37
     Er
    0.36
    Eureka
    0.36
     syl
    0.35
    Bro
    0.35
    Scatter
    0.35
    Activations Density 0.001%

    No Known Activations