© 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. 4176
    Prev
    Next
    INDEX
    Explanations

    strings of numbers with interspersed punctuation, likely representing scientific measurements or identifiers

    oai_token-act-pair · gemini-2.0-flash

    Middle Eastern names/places

    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
     navideñas
    -0.54
     vermelhas
    -0.52
     dė
    -0.51
     typelib
    -0.50
     meille
    -0.49
    ambung
    -0.48
     laikā
    -0.48
     MenuView
    -0.47
     Orrell
    -0.46
     penonton
    -0.46
    POSITIVE LOGITS
     Maryam
    0.59
     Iran
    0.59
     Ahmad
    0.58
     Kazakhstan
    0.58
     Pakistan
    0.57
     Iranian
    0.56
     Baha
    0.55
     Uzbekistan
    0.54
     Sabah
    0.54
     Indonesia
    0.54
    Activations Density 34.202%

    No Known Activations