© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12204
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biology, genetics, or chemistry

    oai_token-act-pair · gemini-2.0-flash

    Scientific samples

    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
     متعلقه
    -0.94
     calendriers
    -0.72
    postIndex
    -0.70
     AssemblyCulture
    -0.65
    Références
    -0.60
    ValueStyle
    -0.60
    Atsauces
    -0.59
     kaynağından
    -0.59
    mones
    -0.58
     initComponents
    -0.58
    POSITIVE LOGITS
     culture
    0.68
     population
    0.65
     sample
    0.56
    culture
    0.54
    ēj
    0.54
     preparation
    0.52
    population
    0.50
    исленность
    0.50
     record
    0.50
    GEBURTS
    0.48
    Activations Density 10.719%

    No Known Activations