© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12659
    Prev
    Next
    INDEX
    Explanations

    mentions of pairs of items

    oai_token-act-pair · gemini-2.0-flash

    pair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    com
    -0.44
    ystic
    -0.43
    織
    -0.43
    aka
    -0.42
     EventArgs
    -0.41
    piac
    -0.41
    ahuila
    -0.41
     BIBSYS
    -0.40
     impurity
    -0.40
     olio
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.95
    Хьажоргаш
    0.87
    دانشنامهٔ
    0.82
    argout
    0.75
    Datuak
    0.73
    MessageOf
    0.72
    thington
    0.71
     snippetHide
    0.70
    queryInterface
    0.64
    Hentet
    0.64
    Activations Density 1.312%

    No Known Activations