© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236530
    Prev
    Next
    INDEX
    Explanations

    generating primes up to n

    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_32_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
     setup
    0.41
     fronte
    0.40
    oints
    0.39
     நிர
    0.38
    фро
    0.37
    Фран
    0.37
     smartest
    0.37
    䐈
    0.37
     isolates
    0.37
    setup
    0.36
    POSITIVE LOGITS
     RANGE
    0.38
    éns
    0.38
     pelanggan
    0.38
     Kale
    0.37
     যশোর
    0.37
     Plex
    0.37
     "<
    0.36
     受け
    0.36
     feta
    0.36
    葷
    0.36
    Activations Density 0.009%

    No Known Activations