© 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. 6643
    Prev
    Next
    INDEX
    Explanations

    a variety of common words, but seems to be triggered most strongly by the expression "way".

    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_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
    ViewFeatures
    -0.81
    {"
    -0.73
    ""}
    -0.68
     nakalista
    -0.68
    存于互联网档案馆
    -0.66
     ModelExpression
    -0.64
    rungsseite
    -0.62
     {"
    -0.62
    $("#
    -0.58
    \}}
    -0.58
    POSITIVE LOGITS
     ‘
    3.03
     '
    3.02
     ‚
    2.14
     ’
    2.08
    『
    1.97
     (‘
    1.94
    ='
    1.77
     ('
    1.77
    、『
    1.74
    ('
    1.70
    Activations Density 10.846%

    No Known Activations