© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10001
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that set the tone or emphasis of a sentence

    oai_token-act-pair · gemini-2.0-flash

    strong

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     المعيارى
    -0.78
    IntoConstraints
    -0.71
    исленность
    -0.65
    EDEFAULT
    -0.64
     @"/
    -0.63
    出版年
    -0.60
     Waray
    -0.60
    Tembelea
    -0.59
    ValueStyle
    -0.59
     GenerationType
    -0.59
    POSITIVE LOGITS
     strong
    1.84
     Strong
    1.52
    strong
    1.48
    Strong
    1.47
     STRONG
    1.34
     stronger
    1.23
    STRONG
    1.23
     sterke
    1.20
     solid
    1.16
     strongest
    1.13
    Activations Density 1.695%

    No Known Activations