© 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. 137901
    Prev
    Next
    INDEX
    Explanations

    ```cpp includes```

    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
     milion
    0.38
     Ka
    0.38
     KAP
    0.37
    álen
    0.37
     kap
    0.37
    жин
    0.36
    ▔
    0.36
     Rud
    0.36
    Kap
    0.36
     Ett
    0.35
    POSITIVE LOGITS
    娌
    0.37
    ས་
    0.36
    thrift
    0.36
    otide
    0.36
     saff
    0.36
     stimulated
    0.35
    த்ய
    0.35
     catch
    0.35
     mainly
    0.35
     utilizados
    0.35
    Activations Density 0.003%

    No Known Activations