© 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. 12113
    Prev
    Next
    INDEX
    Explanations

    HTML markup, datestamps, titles of documents, names, and numbers, especially in list formats

    oai_token-act-pair · gemini-2.0-flash

    HTML/code snippets

    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
    </b>
    -0.47
     differentiation
    -0.41
     mineralization
    -0.40
    <b>
    -0.40
     parallelism
    -0.40
     thickening
    -0.39
    </h5>
    -0.39
     infinitesimal
    -0.39
     independence
    -0.38
    󠁢
    -0.38
    POSITIVE LOGITS
    -
    0.88
    ,
    0.76
    writeFieldEnd
    0.67
     Dostupné
    0.66
    setViewName
    0.64
     estekak
    0.64
    :
    0.63
    : 
    0.60
     beginnetje
    0.59
     :—
    0.59
    Activations Density 16.351%

    No Known Activations