© 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. 11277
    Prev
    Next
    INDEX
    Explanations

    text from scientific or mathematical literature, especially formulas and references.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns and special symbols

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

    and

    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
    ConstraintMaker
    -0.86
     للمعارف
    -0.83
     Wikispecies
    -0.80
    neſs
    -0.79
    makeConstraints
    -0.79
    RetentionPolicy
    -0.78
     otomatig
    -0.77
     saites
    -0.75
    writeFieldEnd
    -0.75
    ."));
    -0.74
    POSITIVE LOGITS
     its
    0.45
     his
    0.45
     their
    0.44
     
    0.44
     -
    0.43
     endforeach
    0.42
     ::
    0.42
    ↵
    0.41
     my
    0.40
    anwal
    0.40
    Activations Density 14.118%

    No Known Activations