© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    capitalized words and phrases related to India, specifically around place names and universities.

    oai_token-act-pair · gemini-2.0-flash

    India/Bangladesh contexts

    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
    writeField
    -0.61
    thâu
    -0.57
     виправивши
    -0.55
     emm
    -0.55
    kháu
    -0.53
    ArrowToggle
    -0.52
    ComponentName
    -0.48
    ubre
    -0.47
     Rocca
    -0.47
    ItemBackground
    -0.47
    POSITIVE LOGITS
     nakalista
    0.73
    ngdoc
    0.59
     tribal
    0.57
    Skocz
    0.56
    AxisAlignment
    0.56
    tagHelperRunner
    0.55
    setVerticalGroup
    0.55
    aguchi
    0.54
    nloa
    0.52
    rungsseite
    0.52
    Activations Density 3.874%

    No Known Activations