© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35610
    Prev
    Next
    INDEX
    Explanations

    matrix or board structure

    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_31_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
     Salzburg
    0.33
    \|^
    0.33
     innocent
    0.32
    )^
    0.31
     achromatic
    0.31
     >
    0.31
    στη
    0.30
     spill
    0.30
     predecessors
    0.30
    …
    0.30
    POSITIVE LOGITS
    lide
    0.35
     টেলিভিশন
    0.34
    Live
    0.34
     матри
    0.33
     διαφο
    0.33
    FinishLaunching
    0.33
    cluse
    0.33
     Matrix
    0.32
    uluk
    0.32
     घास
    0.32
    Activations Density 0.005%

    No Known Activations