© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15423
    Prev
    Next
    INDEX
    Explanations

    names of religious institutions as well as short initialisms (e.g. "la" and "el")

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.60
     EconPapers
    -0.57
    下载附件
    -0.52
     Stefani
    -0.51
    Diweddarwch
    -0.49
    Autoritní
    -0.49
    HtmlAttribute
    -0.49
    Geplaatst
    -0.48
    LoggerFactory
    -0.48
    patine
    -0.48
    POSITIVE LOGITS
     Efq
    0.53
    solicited
    0.52
     étoit
    0.51
    matchCondition
    0.51
    quele
    0.49
     Dij
    0.49
    rungsseite
    0.49
     rajut
    0.47
    queles
    0.47
    Sé
    0.47
    Activations Density 0.370%

    No Known Activations