© 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. 8588
    Prev
    Next
    INDEX
    Explanations

    location words, especially when combined with sciencey words

    oai_token-act-pair · gemini-2.0-flash

    Spread across different entities

    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
    Across
    -1.93
     Across
    -1.91
     across
    -1.91
    across
    -1.87
     ACROSS
    -1.77
     throughout
    -1.58
    throughout
    -1.50
     Throughout
    -1.36
    Throughout
    -1.30
     THRO
    -1.06
    POSITIVE LOGITS
    SharedDtor
    0.63
    complexContent
    0.60
    $}}
    0.58
     BoxFit
    0.58
    httphttps
    0.56
     wireType
    0.54
     defStyleAttr
    0.53
    >
    0.52
     ac
    0.51
    RectangleBorder
    0.51
    Activations Density 4.094%

    No Known Activations