© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10372
    Prev
    Next
    INDEX
    Explanations

    quotation marks and related punctuation, and specific words associated with marketing, societal change, and sewing.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -
    -1.15
    ,
    -1.01
     (
    -0.99
     “
    -0.92
     B
    -0.90
     der
    -0.87
     per
    -0.86
     et
    -0.83
     y
    -0.82
     von
    -0.82
    POSITIVE LOGITS
     itſelf
    1.72
     myſelf
    1.41
     pleaſure
    1.36
     ་་
    1.36
     Monfieur
    1.34
    ſelf
    1.31
     Jefus
    1.30
    ſelves
    1.24
     themſelves
    1.23
     Theſe
    1.23
    Activations Density 17.258%

    No Known Activations