© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15882
    Prev
    Next
    INDEX
    Explanations

    words about events that are happening or have occurred

    oai_token-act-pair · gemini-2.0-flash

    "to be" verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    VersionUID
    -0.72
     bezeichneter
    -0.58
    +#+
    -0.58
    GHIJKLM
    -0.57
    pone
    -0.56
    postIndex
    -0.56
    tay
    -0.51
    麗
    -0.50
    NameInMap
    -0.50
    ിയ
    -0.48
    POSITIVE LOGITS
    matite
    0.58
     Unsc
    0.56
    Lähteet
    0.54
    χρι
    0.53
     Comprometido
    0.52
    EndGlobalSection
    0.51
    Etimo
    0.51
     esfuer
    0.51
    MLLoader
    0.50
    المناصب
    0.50
    Activations Density 45.331%

    No Known Activations