© 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. 14915
    Prev
    Next
    INDEX
    Explanations

    references to Indonesia, Java and Jakarta, or mentions of formula milk.

    oai_token-act-pair · 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
     Indonesian
    -1.34
     Indonesia
    -1.32
     Indones
    -1.13
    Indonesia
    -1.13
     INDONESIA
    -0.94
     Indon
    -0.90
     indonesia
    -0.82
     Jakarta
    -0.82
     Malaysian
    -0.69
    Jakarta
    -0.66
    POSITIVE LOGITS
    <bos>
    0.66
    WebServlet
    0.63
    (!__
    0.60
     Gorb
    0.60
     GoogleFonts
    0.60
    >{@
    0.57
    ValueStyle
    0.57
    borderSide
    0.55
     GenerationType
    0.55
    PostMapping
    0.54
    Activations Density 0.706%

    No Known Activations