© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144791
    Prev
    Next
    INDEX
    Explanations

    bifold wallet

    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_0_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
    ა
    1.91
    م
    1.82
    ت
    1.82
    at
    1.77
    dır
    1.52
    AN
    1.43
    ﺕ
    1.35
    A
    1.34
    П
    1.34
    ምት
    1.33
    POSITIVE LOGITS
    iden
    1.26
    ի
    1.21
    ض
    1.16
     UAV
    1.14
     elke
    1.12
    的样子
    1.10
     is
    1.09
    ัง
    1.09
    ও
    1.04
     OC
    1.02
    Activations Density 0.000%

    No Known Activations