© 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. 219481
    Prev
    Next
    INDEX
    Explanations

    quadratic equation

    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
    滋
    0.45
    δει
    0.40
    惹
    0.40
    вори
    0.39
    Complexity
    0.37
    Опера
    0.37
    Rav
    0.36
    overs
    0.36
     enchantment
    0.36
    Kir
    0.35
    POSITIVE LOGITS
    률
    0.42
     Nev
    0.42
    率は
    0.41
     L
    0.40
     Southeastern
    0.40
    rokken
    0.39
     hemorrh
    0.38
     equaling
    0.38
    inander
    0.38
     initiatives
    0.38
    Activations Density 0.004%

    No Known Activations