© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260760
    Prev
    Next
    INDEX
    Explanations

    creation and annihilation operators

    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_5_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
    j
    1.50
    ون
    1.22
    1
    1.20
    د
    1.20
    d
    1.16
    t
    1.11
    لى
    1.10
    ہ
    1.09
    б
    1.07
    و
    1.06
    POSITIVE LOGITS
    is
    1.59
     σε
    1.13
    는
    1.08
    on
    1.00
     rheumatoid
    0.99
    he
    0.98
     ی
    0.96
     NIM
    0.93
     в
    0.91
    ใน
    0.91
    Activations Density 0.000%

    No Known Activations