© 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. 5647
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms, especially those involving contracts, payments, and obligations

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "default"

    np_token-act-pair-logits · gpt-4o-mini

    default

    np_max-act-logits · gemini-2.0-flash
    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
    Geplaatst
    -0.52
     Villa
    -0.51
    ERICK
    -0.51
     Lonely
    -0.49
     Potts
    -0.49
    contributions
    -0.49
     villa
    -0.48
     neutralizing
    -0.47
    Villa
    -0.47
    omiast
    -0.46
    POSITIVE LOGITS
     default
    1.63
    default
    1.38
     defaults
    1.37
     Default
    1.28
     defaulted
    1.22
    Default
    1.20
     DEFAULT
    1.12
    デフォ
    1.00
     Defaults
    0.97
     defa
    0.93
    Activations Density 3.976%

    No Known Activations