© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8990
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives clustered near related nouns

    oai_token-act-pair · gemini-2.0-flash

    personal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     HasFactory
    -0.69
    PerformLayout
    -0.67
     jScrollPane
    -0.67
    mybatisplus
    -0.66
     BoxDecoration
    -0.66
    Eksteraj
    -0.58
    étit
    -0.57
    esez
    -0.56
     initComponents
    -0.55
    kadot
    -0.55
    POSITIVE LOGITS
     personal
    1.61
     Personal
    1.58
    Personal
    1.54
    personal
    1.50
     PERSONAL
    1.27
    PERSONAL
    1.21
     persönliche
    1.08
     personally
    0.98
     persönlichen
    0.97
     personales
    0.92
    Activations Density 2.143%

    No Known Activations