© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7152
    Prev
    Next
    INDEX
    Explanations

    ```code```

    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_39_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
     stars
    0.39
     రామ
    0.39
     bars
    0.39
    запа
    0.38
    ೀ
    0.36
    bigcap
    0.35
     TRY
    0.35
     запи
    0.34
    ிருக்க
    0.34
    申し上げ
    0.34
    POSITIVE LOGITS
    檴
    0.47
    Dos
    0.46
    Shortly
    0.42
    assume
    0.42
     "\(
    0.39
     funz
    0.38
    
    0.38
    Default
    0.38
    谦
    0.38
    聑
    0.38
    Activations Density 0.012%

    No Known Activations