Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14910
    Prev
    Next
    INDEX
    Explanations

    punctuation and other tokens associated with the beginnings and ends of clauses, sentences and parenthetical statements.

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
     including
    -0.90
     incluindo
    -0.81
     GenerationType
    -0.79
    AndroidJUnit
    -0.78
    =$?
    -0.77
     estekak
    -0.77
    ^(@)
    -0.77
     ossia
    -0.77
     czyli
    -0.76
    antaranya
    -0.75
    POSITIVE LOGITS
    ,
    0.47
    igata
    0.46
     désolés
    0.45
    要
    0.45
    الحياه
    0.43
    сшта
    0.43
     Isles
    0.42
    末
    0.42
    ча
    0.41
     mere
    0.41
    Activations Density 1.117%

    No Known Activations