© 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. 279
    Prev
    Next
    INDEX
    Explanations

    words indicating importance or size, and words associated with the UK

    oai_token-act-pair · gemini-2.0-flash

    big/huge

    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
    epam
    -0.59
    ntlet
    -0.57
     big
    -0.57
    żym
    -0.55
    Huge
    -0.52
    bigger
    -0.52
    бла
    -0.51
     BIG
    -0.51
    BIG
    -0.50
     grandi
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.67
     Meksiku
    0.60
     kaynağından
    0.59
     betweenstory
    0.58
     MessageBoxIcon
    0.57
    FunctionFlags
    0.56
     &___
    0.56
    (!__
    0.55
    sidemargin
    0.54
     sī
    0.54
    Activations Density 7.017%

    No Known Activations