© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216928
    Prev
    Next
    INDEX
    Explanations

    powers and equations

    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
     panic
    0.39
    dr
    0.38
    ered
    0.37
     chaos
    0.36
     kompon
    0.35
    {:
    0.35
     simulations
    0.34
     stitches
    0.34
     кожного
    0.34
    plasma
    0.34
    POSITIVE LOGITS
     cashback
    0.42
    ICOS
    0.41
     attachments
    0.39
     direita
    0.38
     ఉద్య
    0.38
    Comunic
    0.38
    зья
    0.38
    諜
    0.38
     apex
    0.38
     esquerda
    0.37
    Activations Density 0.000%

    No Known Activations