© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7895
    Prev
    Next
    INDEX
    Explanations

    the word "formal" and sometimes a following number

    oai_token-act-pair · gemini-2.0-flash

    formal

    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
     pleaſure
    -1.45
    AndEndTag
    -1.43
     Efq
    -1.33
     Monfieur
    -1.33
     myſelf
    -1.27
     ſeveral
    -1.24
     Majefty
    -1.23
     Chriftian
    -1.22
     himſelf
    -1.20
     unknownFields
    -1.18
    POSITIVE LOGITS
    ,
    0.80
     on
    0.70
    </em>
    0.68
     it
    0.64
     over
    0.63
     du
    0.63
     so
    0.63
    </i>
    0.63
     an
    0.62
     do
    0.62
    Activations Density 0.482%

    No Known Activations