© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4453
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'profit' or 'SQL', sometimes with related surrounding terms

    oai_token-act-pair · gemini-2.0-flash

    non-profits and NoSQL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     estimés
    -0.79
    ConstraintMaker
    -0.79
     Meksiku
    -0.78
    ArgsConstructor
    -0.77
    الإنجليزية
    -0.72
    SceneManagement
    -0.68
    ValueStyle
    -0.68
    adpleegd
    -0.67
     Савезне
    -0.66
    }\]
    -0.66
    POSITIVE LOGITS
    DebuggerNonUser
    0.48
    maphore
    0.47
     tij
    0.47
     урна
    0.47
    TypeString
    0.45
     favourite
    0.43
     favorite
    0.42
    ulum
    0.42
    переди
    0.41
     FormData
    0.41
    Activations Density 1.038%

    No Known Activations