© 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. 5972
    Prev
    Next
    INDEX
    Explanations

    words related to healthcare and economics in developing countries, or words related generally to infrastructure problems

    oai_token-act-pair · gemini-2.0-flash

    moiselle

    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
    AndEndTag
    -0.61
    NameInMap
    -0.60
    URLException
    -0.60
    ChildScrollView
    -0.56
    bootstrapcdn
    -0.53
    İstinadlar
    -0.53
    titleMargin
    -0.53
    fjspx
    -0.52
    newArrayList
    -0.52
    BASEPATH
    -0.51
    POSITIVE LOGITS
    moiselle
    0.57
    atriz
    0.56
    Mediabestanden
    0.47
     ไทย
    0.46
    atrix
    0.46
    trường
    0.46
    /−
    0.46
    rene
    0.45
    datastore
    0.44
    ᐟ
    0.44
    Activations Density 4.101%

    No Known Activations