© 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. 32064
    Prev
    Next
    INDEX
    Explanations

    select or selection

    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
    সারে
    0.48
    声
    0.36
    ায়ত্ত
    0.35
    сора
    0.35
     мая
    0.35
     foams
    0.35
     Waters
    0.34
    *}\
    0.34
     finishes
    0.34
     لص
    0.34
    POSITIVE LOGITS
     selectivity
    0.45
    我想
    0.44
     xrd
    0.41
    SelectSingle
    0.41
     IPF
    0.40
    ிறேன்
    0.40
    霹
    0.39
    selective
    0.39
    อุ
    0.38
     Select
    0.38
    Activations Density 0.006%

    No Known Activations