© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5249
    Prev
    Next
    INDEX
    Explanations

    code snippets with a mix of programming languages (likely JavaScript and C) with non-English (Spanish/Portuguese) comments/text interspersed and possibly related to decrementing a counter within a loop

    oai_token-act-pair · gemini-2.0-flash

    and (various languages)

    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
    WithFormat
    -0.49
      (
    -0.48
    kloped
    -0.48
    servez
    -0.48
     Vikipedi
    -0.47
     whatnot
    -0.47
    ouille
    -0.46
    JspWriter
    -0.46
    참고
    -0.46
     y
    -0.46
    POSITIVE LOGITS
     and
    2.81
    and
    1.52
    และ
    1.20
     và
    1.14
    和
    1.11
     AND
    1.05
     и
    1.04
     And
    0.96
     그리고
    0.96
     और
    0.95
    Activations Density 0.294%

    No Known Activations