© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    phrases that have the word "more" in close proximity or words denoting an increase or deficit

    oai_token-act-pair · gemini-2.0-flash

    Increasing

    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
    opcao
    -0.48
    kowski
    -0.46
    openapi
    -0.45
    off
    -0.44
    eksi
    -0.44
    льности
    -0.42
     off
    -0.40
    lanmış
    -0.40
    agal
    -0.39
    Toole
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    1.03
     ExecuteAsync
    0.93
     doInBackground
    0.91
     defaultstate
    0.89
     Biôgrafia
    0.85
     AssemblyCompany
    0.83
     SwitchCompat
    0.83
    LLocation
    0.82
    存于互联网档案馆
    0.81
     Theſe
    0.79
    Activations Density 0.659%

    No Known Activations