© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32141
    Prev
    Next
    INDEX
    Explanations

    absolute best

    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_40_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
    ikums
    0.42
     най
    0.41
     scarcity
    0.39
     loc
    0.38
    槙
    0.38
     pillars
    0.37
     monomers
    0.37
    睦
    0.37
     пер
    0.36
    Tried
    0.36
    POSITIVE LOGITS
     principalTable
    0.44
     sahibi
    0.38
     desean
    0.37
    祅
    0.36
    lje
    0.35
    MouseEnter
    0.35
     deseas
    0.35
    STONE
    0.35
    StartZ
    0.34
    termilk
    0.34
    Activations Density 0.000%

    No Known Activations