© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12720
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    oai_token-act-pair · gemini-2.0-flash

    research and analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    
    -0.98
    Personendaten
    -0.85
     <<<<<<<<<<<<<<
    -0.83
    ंदीखरीदारी
    -0.82
     wireType
    -0.78
    IntoConstraints
    -0.75
    complexType
    -0.75
    medriver
    -0.75
     nakalista
    -0.75
    CodedInputStream
    -0.73
    POSITIVE LOGITS
    мель
    0.48
     induction
    0.44
    ter
    0.42
     tham
    0.41
    ta
    0.41
    ्य
    0.40
     moves
    0.39
    induction
    0.38
    Throwable
    0.38
    do
    0.36
    Activations Density 4.982%

    No Known Activations