© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 644
    Prev
    Next
    INDEX
    Explanations

    words related to intentions, purpose and feelings

    oai_token-act-pair · gemini-2.0-flash

    personal beliefs and opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Being
    -1.33
     Being
    -1.30
    being
    -1.20
     being
    -1.15
     BEING
    -1.10
    Getting
    -1.06
     Getting
    -1.02
    getting
    -1.02
    Becoming
    -0.94
     Becoming
    -0.93
    POSITIVE LOGITS
    SharedDtor
    0.47
    FXML
    0.45
    useEffect
    0.42
     insulted
    0.42
     condolences
    0.41
    entown
    0.40
    ⓘ
    0.40
    RefNanny
    0.39
    prüche
    0.39
     Lordships
    0.38
    Activations Density 6.186%

    No Known Activations