© 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
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 235023
    Prev
    Next
    INDEX
    Explanations

    funding, salary, and costs

    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
    oretto
    0.45
    ይል
    0.39
    Permanent
    0.39
    媢
    0.38
    uncle
    0.38
     ಮಹಿ
    0.38
    olateral
    0.38
    겟
    0.38
     അധിക
    0.37
     permanente
    0.36
    POSITIVE LOGITS
     γε
    0.35
    err
    0.34
     अश्व
    0.33
     Ganges
    0.32
     steeds
    0.32
    ext
    0.32
     herald
    0.32
    QRCode
    0.32
    imod
    0.32
     hina
    0.32
    Activations Density 0.001%

    No Known Activations