© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10062
    Prev
    Next
    INDEX
    Explanations

    mentions of language and languages

    oai_token-act-pair · gemini-2.0-flash

    language differences

    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
     springfox
    -0.53
     InputDecoration
    -0.53
    ništ
    -0.52
     JpaRepository
    -0.51
    MENAFN
    -0.50
    datatable
    -0.49
    English
    -0.49
    gráfica
    -0.48
     demen
    -0.47
    EndContext
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.60
    sizeCache
    0.59
     发表于
    0.56
    parsedMessage
    0.52
    GeneratedMessage
    0.52
    poptosis
    0.51
    protoimpl
    0.51
    밌
    0.50
     alſo
    0.49
    Chham
    0.48
    Activations Density 4.985%

    No Known Activations