© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1650
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating urgency or strong emotion, sometimes religious.

    oai_token-act-pair · gemini-2.0-flash

    strong emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    HideFlags
    -0.60
    WireFormatLite
    -0.56
     memoized
    -0.55
     cherchés
    -0.54
     Normdatei
    -0.52
     escalated
    -0.52
     looping
    -0.52
    RectangleBorder
    -0.52
     NgModule
    -0.51
    Портал
    -0.51
    POSITIVE LOGITS
     use
    0.63
     spend
    0.58
     take
    0.58
    riwal
    0.58
    vacy
    0.53
     pass
    0.53
     yourself
    0.53
     HasFactory
    0.53
    ungsbedingungen
    0.53
     don
    0.53
    Activations Density 1.323%

    No Known Activations