© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11288
    Prev
    Next
    INDEX
    Explanations

    angle brackets paired with other tokens and certain programming keywords

    oai_token-act-pair · gemini-2.0-flash

    code and configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    
    -0.64
     crdi
    -0.64
    findpost
    -0.61
    cupa
    -0.61
     marinho
    -0.60
     vulgaires
    -0.60
    buttonBar
    -0.59
     $_"
    -0.59
    AnchorStyles
    -0.58
    keyColumn
    -0.58
    POSITIVE LOGITS
    calibration
    0.50
    affinity
    0.47
    latency
    0.47
    Discriminator
    0.46
    concentration
    0.44
     interpreta
    0.44
    decomposition
    0.43
    isolate
    0.43
    Configs
    0.43
     Preparedness
    0.42
    Activations Density 16.799%

    No Known Activations