© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6794
    Prev
    Next
    INDEX
    Explanations

    instances of the word "persistence" and words related to time or opposition

    oai_token-act-pair · gemini-2.0-flash

    code and time mentions

    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
    <bos>
    -2.20
    ↵↵
    -1.30
    ↵
    -1.09
    '
    -1.00
     and
    -0.82
    ’
    -0.77
    the
    -0.75
    A
    -0.75
     
    -0.69
    <eos>
    -0.68
    POSITIVE LOGITS
    AnchorStyles
    1.02
    ^(@)
    1.00
    ).</
    0.99
    .}~\
    0.97
    !")
    
    0.96
    TagMode
    0.95
     HasFactory
    0.95
    XmlAccessType
    0.91
    ViewFeatures
    0.90
    agisse
    0.89
    Activations Density 3.849%

    No Known Activations