© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204631
    Prev
    Next
    INDEX
    Explanations

    units and quantities

    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
    Four
    0.38
    FOUR
    0.38
     Four
    0.38
    Cra
    0.38
    ressions
    0.37
    Ignoring
    0.37
    🏻
    0.37
    긋
    0.36
    Sounds
    0.36
    ">:
    0.36
    POSITIVE LOGITS
     inclusion
    0.48
    ถูก
    0.41
     gestalt
    0.41
     +
    0.39
     تأس
    0.39
     вклю
    0.38
     scheduler
    0.38
     included
    0.37
     включа
    0.37
     inclus
    0.37
    Activations Density 0.000%

    No Known Activations