© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15964
    Prev
    Next
    INDEX
    Explanations

    a combination of the number 2, parentheses, commas, plus signs, decimals, and the word "taxpayer."

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     in
    -0.51
     to
    -0.46
     or
    -0.40
     
    -0.40
     as
    -0.37
     on
    -0.36
     si
    -0.32
     is
    -0.30
     by
    -0.30
     e
    -0.26
    POSITIVE LOGITS
     Monfieur
    2.02
     itſelf
    1.98
     myſelf
    1.96
     pleaſure
    1.88
     Efq
    1.88
     purpoſe
    1.84
     houſe
    1.84
     ―――――
    1.83
     iſt
    1.80
     Majefty
    1.80
    Activations Density 5.821%

    No Known Activations