© 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. 14256
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    code/hexadecimal

    np_max-act-logits · 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
    st
    -0.52
     Inga
    -0.51
    ims
    -0.48
     coughs
    -0.48
     cysts
    -0.48
     Rosalie
    -0.47
     Republics
    -0.47
     stalling
    -0.47
     tingling
    -0.47
     Sermons
    -0.46
    POSITIVE LOGITS
     Савезне
    0.62
    bonucleic
    0.62
    ftance
    0.61
    uvwxyz
    0.58
    ftant
    0.57
    bonucle
    0.56
    ſtra
    0.54
    imach
    0.54
    qrstuvwxyz
    0.54
     Maz
    0.52
    Activations Density 4.350%

    No Known Activations