© 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. 13889
    Prev
    Next
    INDEX
    Explanations

    scientific language about genetics and proteins

    oai_token-act-pair · gemini-2.0-flash

    genes, cells, strains

    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
     AssemblyTitle
    -0.71
    ChildScrollView
    -0.70
    ReusableCell
    -0.67
    OGND
    -0.65
    Toponymie
    -0.65
     متعلقه
    -0.64
     InputDecoration
    -0.64
    verwijspagina
    -0.63
    WriteBarrier
    -0.60
     ReSharper
    -0.60
    POSITIVE LOGITS
     strain
    0.53
     nakalista
    0.47
    vetica
    0.46
    loz
    0.44
     Mer
    0.44
     strains
    0.43
     Progress
    0.43
     kil
    0.42
    strain
    0.42
    strains
    0.41
    Activations Density 7.907%

    No Known Activations