© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75642
    Prev
    Next
    INDEX
    Explanations

    war and destruction

    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
     testigos
    0.41
     algoritmo
    0.41
    లుగు
    0.39
     алгорит
    0.39
     facilit
    0.39
    砣
    0.37
    өп
    0.37
    {\|
    0.37
     moldings
    0.37
     근무
    0.37
    POSITIVE LOGITS
     Mapper
    0.46
    Defense
    0.41
     Defense
    0.40
     industrielle
    0.40
    phere
    0.38
     Underground
    0.37
     defense
    0.37
     輸入
    0.36
     underground
    0.36
    industrial
    0.36
    Activations Density 0.007%

    No Known Activations