© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215101
    Prev
    Next
    INDEX
    Explanations

    creamy sauces or cheese

    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_31_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
     keratin
    0.39
     nan
    0.38
    国
    0.36
     simple
    0.35
    चारी
    0.35
     methotrexate
    0.35
    資金
    0.35
    olina
    0.34
    山东
    0.34
     basit
    0.34
    POSITIVE LOGITS
     Mest
    0.35
     Kön
    0.34
     Identifying
    0.33
    堣
    0.33
     Traditional
    0.33
    몸
    0.33
    Traditional
    0.32
     Estimate
    0.32
     Employees
    0.32
     ፈ
    0.32
    Activations Density 0.006%

    No Known Activations