© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6607
    Prev
    Next
    INDEX
    Explanations

    common short words, especially prepositions and pronouns

    oai_token-act-pair · gemini-2.0-flash

    snippets of web text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Wiktionnaire
    -0.54
    onatos
    -0.52
    DebuggerNonUser
    -0.50
     philosophie
    -0.50
     conspic
    -0.49
    voegen
    -0.49
     philosophies
    -0.48
    otels
    -0.48
    createStatement
    -0.48
    
    -0.47
    POSITIVE LOGITS
     دیکھیے
    0.79
    Personendaten
    0.75
     nakalista
    0.69
    Erreferentziak
    0.64
    StructEnd
    0.63
     تانيه
    0.61
    ArrowToggle
    0.60
    EndContext
    0.59
     кӀ
    0.57
     JADX
    0.56
    Activations Density 2.620%

    No Known Activations