© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123875
    Prev
    Next
    INDEX
    Explanations

    ```go fmt```

    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_37_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
     sinking
    0.41
    гу
    0.38
     sink
    0.37
    ョ
    0.36
     VF
    0.36
     uitvoering
    0.36
    ='/
    0.36
    antages
    0.36
    Sink
    0.36
    =",
    0.35
    POSITIVE LOGITS
     shops
    0.42
     shop
    0.38
     Ret
    0.38
    omn
    0.38
     Shops
    0.38
     fotografia
    0.37
    Euph
    0.37
     chromatographed
    0.37
    aremos
    0.36
     फ़ोन
    0.36
    Activations Density 0.000%

    No Known Activations