© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12351
    Prev
    Next
    INDEX
    Explanations

    code related terms such as vpn, parameters, function and unmarshaller

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     незавершена
    -0.95
    <bos>
    -0.91
     تضيفلها
    -0.89
     Meksiku
    -0.89
     surla
    -0.87
     <<<<<<<<<<<<<<
    -0.84
    tonode
    -0.84
    MLLoader
    -0.81
    __':
    -0.81
    }$.\\
    -0.79
    POSITIVE LOGITS
    AutoField
    0.56
     át
    0.37
    вто
    0.36
     innebär
    0.36
     grossa
    0.35
     quebra
    0.35
    perties
    0.33
    intenant
    0.33
    OnDelete
    0.32
     sole
    0.32
    Activations Density 48.250%

    No Known Activations