© 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. 176664
    Prev
    Next
    INDEX
    Explanations

    URLs and links

    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
    ives
    0.50
     capi
    0.48
     s
    0.47
     hir
    0.47
     fr
    0.45
     spe
    0.44
    isors
    0.42
     l
    0.41
     dz
    0.40
    ines
    0.40
    POSITIVE LOGITS
    apanicola
    0.43
    伍章
    0.42
     الاج
    0.39
    हुन्छ
    0.39
    ocf
    0.38
     Expensive
    0.38
     اجازت
    0.38
    ﻉ
    0.38
    帙
    0.37
     )।
    0.36
    Activations Density 0.008%

    No Known Activations