© 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. 252762
    Prev
    Next
    INDEX
    Explanations

    C

    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
     pick
    0.40
     bequest
    0.40
     "./
    0.39
    ("#
    0.38
     calculateur
    0.38
    .¹
    0.38
    ‌آ
    0.38
    agnie
    0.37
    ዋል።
    0.37
     totalSupply
    0.36
    POSITIVE LOGITS
    planted
    0.39
     கோ
    0.37
     recruiting
    0.36
    министра
    0.36
    ੍ਹਾਂ
    0.36
    ରେ
    0.35
     BYTE
    0.35
    \")
    0.34
    置
    0.34
    planting
    0.34
    Activations Density 0.001%

    No Known Activations