© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198985
    Prev
    Next
    INDEX
    Explanations

    adjudicating rules

    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
     która
    0.62
     οποία
    0.57
    깎
    0.53
    Pal
    0.52
    URL
    0.50
    감
    0.49
    ซึ่ง
    0.49
    Filler
    0.49
     která
    0.48
    AUGUST
    0.48
    POSITIVE LOGITS
    ienten
    0.59
     stimulating
    0.53
     aktivit
    0.51
    வியை
    0.50
    数值
    0.49
     Schemes
    0.48
     ]
    0.48
     variabel
    0.47
    ឆ
    0.47
     clinicians
    0.47
    Activations Density 0.001%

    No Known Activations