© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    code relating to user interface objects and data access

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     purpoſe
    -0.99
     pleaſure
    -0.90
    ſelf
    -0.88
     houſe
    -0.85
     ſche
    -0.84
     Reſ
    -0.83
     ſever
    -0.81
     pouvoit
    -0.81
     feroit
    -0.81
     auroit
    -0.81
    POSITIVE LOGITS
    RegistryLite
    0.88
    BeginContext
    0.71
    addCriterion
    0.65
     الحره
    0.61
    yntaxException
    0.60
     surla
    0.60
    '
    0.59
    localctx
    0.57
    ↵↵
    0.56
     ***!
    0.56
    Activations Density 3.677%

    No Known Activations