© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168639
    Prev
    Next
    INDEX
    Explanations

    you

    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_56_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
     involved
    0.83
     Involved
    0.76
    involved
    0.70
     envolv
    0.61
    左
    0.56
     left
    0.54
     LEFT
    0.49
     terlibat
    0.48
     betrokken
    0.48
     左
    0.46
    POSITIVE LOGITS
     followed
    0.54
    followed
    0.49
     seguido
    0.47
     planned
    0.46
    Planned
    0.46
    planned
    0.44
     seguida
    0.43
     fuelled
    0.41
     suivie
    0.40
    Party
    0.39
    Activations Density 0.005%

    No Known Activations