© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104879
    Prev
    Next
    INDEX
    Explanations

    molecular organic

    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_44_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
    ()>
    0.40
     قان
    0.38
    uzet
    0.37
    Bis
    0.37
    cede
    0.36
    郋
    0.35
    dlg
    0.34
     McE
    0.34
    Florence
    0.34
     同
    0.34
    POSITIVE LOGITS
     matter
    0.50
    matter
    0.48
     물질
    0.48
     вещества
    0.45
     MATTER
    0.44
     fertilizer
    0.44
    يبة
    0.43
     Apex
    0.43
     matière
    0.42
     fertilizers
    0.42
    Activations Density 0.001%

    No Known Activations