© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133677
    Prev
    Next
    INDEX
    Explanations

    smog

    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_6_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
    1.03
     a
    0.99
    ”
    0.95
    "
    0.95
     of
    0.92
    ص
    0.92
    ]
    0.86
     to
    0.84
    سم
    0.84
    us
    0.83
    POSITIVE LOGITS
    ↵
    0.88
    的名字
    0.86
    的力量
    0.85
    的核心
    0.84
     производителя
    0.81
     μια
    0.81
     உட்பட
    0.79
    的形式
    0.79
    च्या
    0.77
     குறித்த
    0.75
    Activations Density 0.000%

    No Known Activations