© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4829
    Prev
    Next
    INDEX
    Explanations

    website names (especially youtube, facebook, github, wordpress, forum, and standard)

    oai_token-act-pair · gemini-2.0-flash

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    addCriterion
    -0.69
    clyde
    -0.50
    BASEPATH
    -0.50
    Cyfeiriadau
    -0.49
     Jungen
    -0.49
    (!__
    -0.47
     (!__
    -0.46
     uska
    -0.45
    映
    -0.45
    WriteAttribute
    -0.44
    POSITIVE LOGITS
    com
    1.58
     com
    1.56
    Com
    1.21
     Com
    1.14
    COM
    1.10
    coms
    1.03
     COM
    0.94
    org
    0.88
     org
    0.88
    coma
    0.83
    Activations Density 0.597%

    No Known Activations