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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9966
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses mentioning something to do before some other action.

    oai_token-act-pair · gemini-2.0-flash

    before something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Hozzáférés
    -0.59
     disambiguazione
    -0.54
    Portail
    -0.53
    GEBURTSDATUM
    -0.53
     nakalista
    -0.52
    CastException
    -0.51
     Процитовано
    -0.51
    例文帳に追加
    -0.51
    rungsseite
    -0.50
     Spokes
    -0.48
    POSITIVE LOGITS
     prelimin
    0.64
    @[+][
    0.63
     دیکھیے
    0.53
     @"/
    0.52
    Depot
    0.51
    niająca
    0.51
    oceros
    0.51
    ConverterFactory
    0.51
    aziland
    0.50
    enoid
    0.50
    Activations Density 0.177%

    No Known Activations