© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200108
    Prev
    Next
    INDEX
    Explanations

    complex concepts

    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_50_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
    ivad
    0.48
    ДА
    0.46
    ари
    0.40
    Proc
    0.39
    И
    0.39
    Da
    0.39
    iven
    0.38
    DA
    0.38
     да
    0.38
    Ca
    0.38
    POSITIVE LOGITS
    rbuf
    0.39
     Moore
    0.38
     mbr
    0.37
    <unused72>
    0.36
     BR
    0.36
     سامنا
    0.36
     Ley
    0.36
     lệ
    0.36
    られます
    0.36
    ﻏ
    0.36
    Activations Density 0.004%

    No Known Activations