© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6561
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sorry."

    oai_token-act-pair · gemini-2.0-flash

    sorry

    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
    v
    -0.99
    l
    -0.99
    p
    -0.98
    1
    -0.95
    m
    -0.94
    ↵
    -0.94
    X
    -0.92
    2
    -0.91
    r
    -0.90
    on
    -0.89
    POSITIVE LOGITS
    ^(@)
    1.60
     ―――――
    1.48
     $_"
    1.40
     ་་
    1.38
    tvguidetime
    1.35
    >\<^
    1.34
     itſelf
    1.34
    ſelves
    1.34
    ſelf
    1.34
    BibitemShut
    1.34
    Activations Density 1.568%

    No Known Activations