© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200220
    Prev
    Next
    INDEX
    Explanations

    ring-fencing

    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_12_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
    on
    0.41
    European
    0.39
     resolv
    0.38
     ribbon
    0.36
    })-
    0.36
    䍜
    0.35
    onload
    0.34
    交易
    0.33
     respir
    0.33
     resale
    0.33
    POSITIVE LOGITS
     Даже
    0.47
     mesmo
    0.46
     by
    0.46
     даже
    0.45
     spese
    0.43
    hamton
    0.43
    mimpi
    0.42
     ചെയ്യാ
    0.41
    ب
    0.41
     сделать
    0.41
    Activations Density 0.001%

    No Known Activations