© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3192
    Prev
    Next
    INDEX
    Explanations

    sections of code, especially in Java, checking for null values, array lengths and conditions

    oai_token-act-pair · gemini-2.0-flash

    null

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    OGND
    -1.09
    MessageOf
    -0.93
    Tikang
    -0.92
     jScrollPane
    -0.91
     esternos
    -0.91
     مرئيه
    -0.90
     EconPapers
    -0.89
     Efq
    -0.89
     transfieras
    -0.85
    BibitemShut
    -0.85
    POSITIVE LOGITS
     and
    0.70
    ↵
    0.64
     ?
    0.60
     
    0.59
     &&
    0.56
     ||
    0.56
    ?
    0.48
    ↵↵
    0.47
    0.45
    +
    0.45
    Activations Density 7.845%
    No Known Activations