© 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. 769
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas or chemical/scientific labels

    oai_token-act-pair · gemini-2.0-flash

    Mixed use of symbols

    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
    DoubleQuotes
    -0.69
    AnchorStyles
    -0.56
    ỳ
    -0.54
    lusconi
    -0.53
     layui
    -0.52
    мум
    -0.52
    XmlAccessType
    -0.50
    ]")]
    -0.50
    uolo
    -0.50
     ret
    -0.49
    POSITIVE LOGITS
     ſtate
    0.78
    ГЛА
    0.77
    subsection
    0.71
     uſe
    0.70
    subsubsection
    0.66
    section
    0.66
     pleaſure
    0.65
     Jefus
    0.65
     Monfieur
    0.65
     ſever
    0.63
    Activations Density 3.270%

    No Known Activations