© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 384
    Prev
    Next
    INDEX
    Explanations

    people introducing themselves

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     VizieR
    -0.60
    posób
    -0.60
    featureID
    -0.59
    tagext
    -0.57
    ConverterFactory
    -0.55
    agents
    -0.54
    ílica
    -0.53
     EconPapers
    -0.53
    Kjelder
    -0.53
    CodedInputStream
    -0.52
    POSITIVE LOGITS
     Dr
    0.77
    Dr
    0.77
     Mr
    0.77
    Mr
    0.74
     Mrs
    0.69
    Mrs
    0.67
     Professor
    0.56
    rufen
    0.56
     Prof
    0.56
     End
    0.54
    Activations Density 0.689%

    No Known Activations