© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93546
    Prev
    Next
    INDEX
    Explanations

    En

    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_60_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
    巴士
    0.41
     lions
    0.39
     deck
    0.38
    भाज
    0.38
     sels
    0.38
     plats
    0.36
    渴望
    0.36
    埗
    0.36
    ود
    0.35
     mog
    0.35
    POSITIVE LOGITS
    est
    0.40
    esy
    0.40
    ടെ
    0.38
    দয়
    0.38
    top
    0.37
    ttt
    0.37
     neighbouring
    0.37
    tyw
    0.37
    ttp
    0.36
    isy
    0.36
    Activations Density 0.001%

    No Known Activations