© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13126
    Prev
    Next
    INDEX
    Explanations

    words related to programming and data structures like array lists and classes, especially in java

    oai_token-act-pair · gemini-2.0-flash

    programming, public service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    LookAnd
    -0.77
     onAnimation
    -0.67
    MLLoader
    -0.67
    #+#
    -0.67
    tagHelperRunner
    -0.65
    ImageContext
    -0.65
    AsUp
    -0.65
    GenerationType
    -0.65
    CompleteListener
    -0.63
    oneofs
    -0.62
    POSITIVE LOGITS
    mobileqq
    0.55
     atras
    0.42
     Deep
    0.42
     verlieren
    0.41
    십시오
    0.41
    Deep
    0.40
    SI
    0.40
    labelControl
    0.40
     risk
    0.40
     Osborn
    0.40
    Activations Density 5.365%

    No Known Activations