© 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. 654
    Prev
    Next
    INDEX
    Explanations

    the relationship between proximity and time within an argument.

    oai_token-act-pair · gemini-2.0-flash

    Nearness or proximity

    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
    Near
    -1.00
     Near
    -0.97
    within
    -0.84
     NEAR
    -0.82
    near
    -0.82
    NEAR
    -0.81
     Nearby
    -0.81
    Within
    -0.81
     Within
    -0.78
     WITHIN
    -0.77
    POSITIVE LOGITS
     closed
    0.59
    rungsseite
    0.57
     closes
    0.54
    énier
    0.50
    Referências
    0.48
    godic
    0.48
     closing
    0.47
    álat
    0.47
     in
    0.46
    헌
    0.46
    Activations Density 2.069%

    No Known Activations