© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6335
    Prev
    Next
    INDEX
    Explanations

    the word 'radiation', and sometimes words like 'or' or 'such' nearby

    oai_token-act-pair · gemini-2.0-flash

    radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.94
    ↵
    -0.92
    _
    -0.83
      
    -0.82
    j
    -0.82
     (
    -0.82
    -
    -0.81
       
    -0.80
    (
    -0.79
    :
    -0.78
    POSITIVE LOGITS
     $_"
    1.47
    ^(@)
    1.41
    BibitemShut
    1.27
     ―――――
    1.26
     Jefus
    1.26
    tershire
    1.24
     Houſe
    1.23
     Efq
    1.20
     définiti
    1.18
     Forumite
    1.16
    Activations Density 1.152%

    No Known Activations