© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5612
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "been"

    oai_token-act-pair · gemini-2.0-flash

    been

    np_max-act-logits · gemini-2.0-flash

    past participles and the word "been"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kaynağından
    -0.83
    @[+][
    -0.77
     سكانية
    -0.68
    ValueStyle
    -0.67
     autorytatywna
    -0.65
    endwhile
    -0.62
    AsUp
    -0.61
    kloped
    -0.60
     législation
    -0.57
    ]")]
    -0.56
    POSITIVE LOGITS
     showcased
    0.52
     misinterpreted
    0.50
     ignored
    0.50
     dumped
    0.49
     purchased
    0.48
    InvalidProtocol
    0.48
    Хро
    0.48
     traced
    0.47
     cleared
    0.47
     scrapped
    0.47
    Activations Density 1.126%

    No Known Activations