© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2248
    Prev
    Next
    INDEX
    Explanations

    planets and space exploration

    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_39_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
     اسرائیل
    0.51
    Israel
    0.46
     Israel
    0.45
     Honolulu
    0.44
     اسرائیلی
    0.44
     immigrants
    0.43
     भारतीयों
    0.41
     J
    0.41
     enroll
    0.41
     immigrant
    0.40
    POSITIVE LOGITS
     planet
    0.95
    planet
    0.88
     Planets
    0.85
    Planet
    0.85
     Planet
    0.83
     planets
    0.80
     плане
    0.80
     planetary
    0.77
     atmosphere
    0.76
     planète
    0.76
    Activations Density 0.155%

    No Known Activations