© 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. 53859
    Prev
    Next
    INDEX
    Explanations

    Magic: The Gathering content

    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
     ভারী
    0.48
     African
    0.46
     wallet
    0.43
     Wallet
    0.42
    African
    0.40
    顐
    0.40
     urn
    0.39
    钱包
    0.39
     republika
    0.38
     ul
    0.38
    POSITIVE LOGITS
     осуществ
    0.36
    способ
    0.35
     зді
    0.35
    饌
    0.35
     импера
    0.35
    даго
    0.35
    чил
    0.34
    ظيم
    0.34
    мости
    0.33
    вез
    0.33
    Activations Density 0.017%

    No Known Activations