© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4124
    Prev
    Next
    INDEX
    Explanations

    words related to demographics, aging, and naming

    oai_token-act-pair · gemini-2.0-flash

    Suffixes "iling" and "aged"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    {§
    -0.46
    λίου
    -0.45
    atikan
    -0.45
    omena
    -0.44
     lenker
    -0.44
    exitRule
    -0.44
    Nimbus
    -0.43
    setMessage
    -0.42
    はじめに
    -0.41
    SizedBox
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.85
     SqlDbType
    0.84
     Monfieur
    0.81
    Datuak
    0.79
     Efq
    0.75
     Theſe
    0.75
     Anſ
    0.73
     myſelf
    0.73
     rhestr
    0.71
     pinulongan
    0.71
    Activations Density 2.208%

    No Known Activations