© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    the number 5 and related citations and versions

    oai_token-act-pair · gemini-2.0-flash

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     beginnetje
    -0.97
    ValueStyle
    -0.93
     AssemblyCompany
    -0.92
    WriteBarrier
    -0.91
    parsedMessage
    -0.87
     sauvages
    -0.86
     Monfieur
    -0.85
    LookAnd
    -0.84
     itſelf
    -0.84
     Савезне
    -0.81
    POSITIVE LOGITS
     National
    0.54
    counter
    0.47
    lassi
    0.46
     ters
    0.46
     num
    0.44
     counter
    0.43
    num
    0.43
     Counter
    0.43
     national
    0.42
     har
    0.42
    Activations Density 0.111%

    No Known Activations