© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    internet URLs using the common domain names youtube.com, github.com, patreon.com or code.google.com and the string 'org'

    oai_token-act-pair · gemini-2.0-flash

    .com

    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
    com
    -0.73
    Com
    -0.62
     Com
    -0.54
     com
    -0.54
     An
    -0.51
     first
    -0.50
     Am
    -0.47
     …
    -0.47
     why
    -0.47
     Max
    -0.46
    POSITIVE LOGITS
    AddHtmlAttribute
    1.04
     tartalomajánló
    0.96
     Мексичка
    0.92
    OGND
    0.90
    PreferredItem
    0.87
    SourceChecksum
    0.84
     nahilalakip
    0.83
     Roskov
    0.83
    цездатний
    0.82
    évaluateur
    0.81
    Activations Density 0.604%

    No Known Activations