© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15279
    Prev
    Next
    INDEX
    Explanations

    values included in scientific studies and news briefs, whether numbers, codes, or political affiliations

    oai_token-act-pair · gemini-2.0-flash

    code and scientific data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     and
    -1.82
     và
    -1.02
     и
    -0.95
    性和
    -0.92
    และ
    -0.89
    子和
    -0.85
     및
    -0.85
     এবং
    -0.82
     ಮತ್ತು
    -0.82
     그리고
    -0.82
    POSITIVE LOGITS
     незавершена
    0.68
    hrad
    0.50
     <<<<<<<<<<<<<<
    0.49
    kuuta
    0.48
     rade
    0.48
     %@",
    0.48
    Jereo
    0.47
    @",
    0.46
    FileDescriptor
    0.46
     perman
    0.45
    Activations Density 5.553%

    No Known Activations