© 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. 204575
    Prev
    Next
    INDEX
    Explanations

    import

    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
    アクセ
    0.39
    }{\
    0.38
     sce
    0.38
     Written
    0.38
     Estates
    0.38
    ಿಗೆ
    0.37
     estates
    0.37
    ]{\
    0.36
    Argentina
    0.36
     Restart
    0.36
    POSITIVE LOGITS
    setVisibility
    0.43
    nim
    0.39
    adies
    0.37
    inputSet
    0.37
     aunts
    0.37
    ictionnaire
    0.37
     மன
    0.36
    ঠোর
    0.36
     이용해서
    0.36
     फ्रैक्शन
    0.36
    Activations Density 0.000%

    No Known Activations