© 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. 213
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words or phrases, in particular those relating to military or government entities and businesses

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    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
    WebVitals
    -0.82
    ArrowToggle
    -0.76
     متعلقه
    -0.75
    ViewFeatures
    -0.73
     '\\;'
    -0.73
    adaptiveStyles
    -0.73
     EconPapers
    -0.71
     ComVisible
    -0.69
    RenderAtEndOf
    -0.68
    __":
    -0.67
    POSITIVE LOGITS
     atve
    0.61
     veiks
    0.60
     darbo
    0.59
     moks
    0.59
     krep
    0.57
    стя
    0.55
     šal
    0.54
    ünst
    0.50
     klinik
    0.49
     gydy
    0.49
    Activations Density 0.152%

    No Known Activations