© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78323
    Prev
    Next
    INDEX
    Explanations

    report crime or complaint

    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_31_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
     Foto
    0.41
     security
    0.40
     सुरक्षा
    0.38
    ورد
    0.38
     spol
    0.36
     purposes
    0.36
    破坏
    0.36
    術
    0.35
     farmed
    0.35
    Radiux
    0.35
    POSITIVE LOGITS
    ,"\
    0.38
     автобу
    0.37
    datasets
    0.36
    льня
    0.36
    Frontend
    0.36
     hina
    0.36
     chast
    0.36
    bmod
    0.36
    Abu
    0.35
     sede
    0.35
    Activations Density 0.001%

    No Known Activations