© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13810
    Prev
    Next
    INDEX
    Explanations

    occurrences of "as" and "if"

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     as
    -0.82
    Rhestr
    -0.76
    ukone
    -0.67
     calendriers
    -0.67
     както
    -0.64
     useRouter
    -0.59
    ofollow
    -0.59
     what
    -0.58
     resourceCulture
    -0.58
     onCancelled
    -0.58
    POSITIVE LOGITS
     needed
    1.11
     necessary
    0.93
    needed
    0.92
     Needed
    0.82
    necessary
    0.79
     required
    0.75
    Needed
    0.74
     Necessary
    0.69
    必要
    0.68
     need
    0.66
    Activations Density 0.538%

    No Known Activations