© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 212550
    Prev
    Next
    INDEX
    Explanations

    trio, duo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
     художника
    1.07
    يل
    1.02
     balanceOf
    1.01
     последствия
    1.00
    న్స్
    0.98
    ث
    0.98
     nových
    0.96
    𝐄
    0.96
     elevationMap
    0.94
     Novem
    0.93
    POSITIVE LOGITS
     on
    1.58
    h
    1.37
    ,
    1.34
    리
    1.24
     as
    1.23
    is
    1.22
    o
    1.21
    ن
    1.16
    on
    1.11
    ↵↵
    1.09
    Activations Density 0.000%

    No Known Activations