© 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. 51770
    Prev
    Next
    INDEX
    Explanations

    solve quadratic equations

    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
     পক্ষে
    0.37
     hoera
    0.35
     perched
    0.34
    usher
    0.34
     generalizes
    0.34
    شتہ
    0.34
    /−
    0.33
     బి
    0.33
     consequ
    0.33
     పరుగులు
    0.33
    POSITIVE LOGITS
     منع
    0.40
     Redirect
    0.36
    爆
    0.36
     dm
    0.35
     spirituality
    0.34
     PPI
    0.34
     Kick
    0.34
     God
    0.34
    宍
    0.34
     سی
    0.33
    Activations Density 0.009%

    No Known Activations