© 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-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4309
    Prev
    Next
    INDEX
    Explanations

    a mix of code, math notation, political commentary, and fragments of a conversation, along with some French words and conjugated verbs

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     have
    -2.17
     has
    -2.00
    Have
    -1.66
    Has
    -1.63
    have
    -1.61
     Have
    -1.59
    has
    -1.53
     Has
    -1.44
     telah
    -1.29
     hebben
    -1.28
    POSITIVE LOGITS
    bootstrapcdn
    0.68
    出版年
    0.68
    TypedDataSet
    0.66
    قایناق‌لار
    0.64
    таратура
    0.63
    Personensuche
    0.59
    mybatisplus
    0.56
     للمعارف
    0.54
     NgModule
    0.52
     Wiktionnaire
    0.51
    Activations Density 2.469%

    No Known Activations