© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50083
    Prev
    Next
    INDEX
    Explanations

    visual representations of data

    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_30_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
    ograd
    0.28
    шении
    0.25
    可以在
    0.25
    ">:
    0.24
    abilirsiniz
    0.24
     Spawn
    0.24
     examining
    0.23
    Spawn
    0.23
     spilling
    0.23
    ContentView
    0.23
    POSITIVE LOGITS
    ICs
    0.26
     ಕಾಲ
    0.22
    責
    0.22
     кам
    0.21
    timed
    0.21
     थरूर
    0.21
     lao
    0.21
    PMorgan
    0.21
     домаћин
    0.20
     объ
    0.20
    Activations Density 0.012%

    No Known Activations