© 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. 4835
    Prev
    Next
    INDEX
    Explanations

    the names of the performers "Susy" and "Geno" and facts about them

    oai_token-act-pair · 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
     autorytatywna
    -0.90
    GEBURTSDATUM
    -0.74
    ьаж
    -0.73
    
    -0.73
    :✨
    -0.73
    Personendaten
    -0.72
     defaultstate
    -0.69
     noqa
    -0.66
    RenderAtEndOf
    -0.65
    دانشنامهٔ
    -0.65
    POSITIVE LOGITS
     MonoBehaviour
    0.52
     toca
    0.47
     InputDecoration
    0.46
    AlterField
    0.46
     AppComponent
    0.45
     BoxDecoration
    0.43
     isti
    0.42
    anggap
    0.41
    AnchorStyles
    0.41
    StringValue
    0.41
    Activations Density 8.109%

    No Known Activations