© 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. 253481
    Prev
    Next
    INDEX
    Explanations

    Python code projects

    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
     project
    0.49
    /}
    0.49
    /
    0.47
     /
    0.47
     projekt
    0.46
     проекта
    0.42
    ／
    0.41
     проект
    0.40
    /,
    0.40
    /^
    0.40
    POSITIVE LOGITS
     stuff
    0.75
    stuff
    0.72
    Stuff
    0.66
     Stuff
    0.64
     stuffs
    0.59
    stuffs
    0.59
     Works
    0.57
    Works
    0.55
    works
    0.52
     codes
    0.49
    Activations Density 0.001%

    No Known Activations