© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201652
    Prev
    Next
    INDEX
    Explanations

    installing

    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_46_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
     glued
    0.88
     affixed
    0.83
     fix
    0.79
    ติด
    0.78
     붙
    0.77
     attach
    0.75
     Fix
    0.75
     pasted
    0.75
     affix
    0.73
     paste
    0.72
    POSITIVE LOGITS
     handle
    0.45
    handle
    0.41
    })}
    0.40
    Handle
    0.39
     바라
    0.37
    coverageStat
    0.37
    HANDLE
    0.36
     Handle
    0.36
    mechanism
    0.35
    pixel
    0.35
    Activations Density 0.002%

    No Known Activations