© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129623
    Prev
    Next
    INDEX
    Explanations

    Armenia

    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
    Negative Logits
    酆
    0.35
     keltiradi
    0.34
    煦
    0.34
    ޅ
    0.34
    峻
    0.34
    ക്കം
    0.33
     Ling
    0.33
    誑
    0.33
    Ｘ
    0.32
    茘
    0.32
    POSITIVE LOGITS
     arm
    3.44
    Arm
    3.14
     Arm
    3.09
    arm
    2.86
     arms
    2.56
     ARM
    2.56
    ARM
    2.50
    arms
    2.25
     Arms
    2.20
     আর্ম
    2.14
    Activations Density 0.001%

    No Known Activations