© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8808
    Prev
    Next
    INDEX
    Explanations

    stems of words frequently used in legal texts.

    oai_token-act-pair · gemini-2.0-flash

    say [the ending -ing, -es, etc.]

    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
    IsContent
    -1.24
    HomeAsUpEnabled
    -1.17
    SourceChecksum
    -1.16
    MemoryWarning
    -1.14
    TagMode
    -1.12
    URLException
    -1.12
    matic
    -1.12
    ments
    -1.10
    ContentAsync
    -1.09
    matics
    -1.09
    POSITIVE LOGITS
    <bos>
    0.16
     piú
    0.13
     egli
    0.13
     și
    0.11
    伊
    0.10
     actuels
    0.09
    Σ
    0.08
    。)
    0.08
     industriels
    0.07
     és
    0.07
    Activations Density 4.253%

    No Known Activations