© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    php code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     acara
    1.36
     Durchführung
    1.35
    לב
    1.35
    钗
    1.34
    ሚ
    1.32
    nano
    1.29
     shouted
    1.25
     Satu
    1.25
    मेट
    1.24
     pegawai
    1.24
    POSITIVE LOGITS
    с
    1.61
     receivable
    1.34
     discomfort
    1.33
    ftÂ
    1.33
    gé
    1.32
     inexist
    1.31
    स
    1.29
     administrativas
    1.28
    仠
    1.27
     Freight
    1.27
    Activations Density 0.044%

    No Known Activations