© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8512
    Prev
    Next
    INDEX
    Explanations

    occurrences of "at", "be", "is," or numerical identifiers, sometimes within the context of ongoing changes, developments, or stressful situations.

    oai_token-act-pair · gemini-2.0-flash

    at/is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PerformLayout
    -0.91
     nahilalakip
    -0.86
     فريبيس
    -0.86
     ProtoMessage
    -0.86
    RegressionTest
    -0.79
     дописавши
    -0.79
    ]--;
    -0.75
    InitVars
    -0.73
    出版年
    -0.73
    SharedCtor
    -0.72
    POSITIVE LOGITS
     at
    2.52
    At
    1.46
     At
    1.41
    at
    1.20
     tại
    1.13
     AT
    0.82
    AtPosition
    0.72
     ở
    0.71
     	e
    0.66
    ณ
    0.65
    Activations Density 2.721%

    No Known Activations