© 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. 5740
    Prev
    Next
    INDEX
    Explanations

    code related to weather data

    oai_token-act-pair · gemini-2.0-flash

    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
     médié
    -0.80
     culturelles
    -0.79
     détruit
    -0.79
     asiatique
    -0.77
     européennes
    -0.77
     validés
    -0.76
     présentés
    -0.75
     fermés
    -0.73
     féminine
    -0.73
     marquées
    -0.73
    POSITIVE LOGITS
    CppMethod
    0.56
     Dus
    0.49
     tian
    0.47
     yz
    0.46
     wu
    0.45
     ee
    0.44
     متعلقه
    0.43
     Soe
    0.43
     quot
    0.43
    ึง
    0.43
    Activations Density 9.748%

    No Known Activations