© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    TLDR summaries

    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_44_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
    百
    0.44
     Hundred
    0.37
     hemic
    0.37
     لله
    0.37
    ֱ
    0.37
    hundred
    0.36
     arro
    0.36
    ี้ยว
    0.36
    services
    0.36
    msgs
    0.35
    POSITIVE LOGITS
    稣
    0.43
    obr
    0.37
     wynosi
    0.37
    स्
    0.37
     Tir
    0.36
    čené
    0.36
    鏘
    0.36
     Wasn
    0.35
     VV
    0.34
    कामा
    0.34
    Activations Density 0.015%

    No Known Activations