© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51132
    Prev
    Next
    INDEX
    Explanations

    arrested, searched, or interrogated

    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_30_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
     চিঠ
    0.41
     rooting
    0.39
    submit
    0.39
     honored
    0.39
     submits
    0.38
    횽
    0.38
    म्मे
    0.38
    netics
    0.38
     root
    0.37
     ROOT
    0.36
    POSITIVE LOGITS
    眼镜
    0.39
    錄
    0.37
     तुर
    0.37
     pemeriksaan
    0.36
    検査
    0.36
     Broker
    0.36
     త
    0.35
     voic
    0.35
    測試
    0.35
    ⾯
    0.35
    Activations Density 0.020%

    No Known Activations