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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6977
    Prev
    Next
    INDEX
    Explanations

    academic paper citations, including author names, journal names, and potentially DOIs

    oai_token-act-pair · gemini-2.0-flash

    Economics research papers

    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
    ValueStyle
    -0.66
    uxxxx
    -0.60
    isks
    -0.57
    ollectionView
    -0.56
    WriteAttribute
    -0.54
     BoxDecoration
    -0.54
     AssemblyCulture
    -0.52
    клопе
    -0.52
     Stretcher
    -0.52
     |]
    -0.52
    POSITIVE LOGITS
    참고
    0.51
    csrf
    0.47
     Newark
    0.43
     Comparative
    0.43
     Kooperation
    0.42
    ukunft
    0.41
    ERIA
    0.41
    MockBean
    0.41
    مصادر
    0.40
     Leopold
    0.40
    Activations Density 9.954%

    No Known Activations