© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 330
    Prev
    Next
    INDEX
    Explanations

    latex or mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    math formulas and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Controllo
    -0.57
    ועל
    -0.56
    Reprints
    -0.53
    mıştır
    -0.53
    adone
    -0.52
    DELL
    -0.51
     unknown
    -0.50
    sified
    -0.49
    FTFY
    -0.48
    ingular
    -0.47
    POSITIVE LOGITS
     resourceCulture
    0.62
     géographique
    0.60
    UrlResolution
    0.59
     ErrIntOverflow
    0.58
    IMPORTED
    0.58
    msgTypes
    0.57
    ExecuteReader
    0.56
    IsContent
    0.54
    StoreMessageInfo
    0.52
    (!__
    0.52
    Activations Density 4.797%

    No Known Activations