© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    words related to user input, data and program output in the context of software programming

    oai_token-act-pair · gemini-2.0-flash

    input

    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
     input
    -2.70
     Input
    -2.47
    input
    -2.44
    Input
    -2.33
     INPUT
    -2.13
     inputs
    -2.08
    INPUT
    -2.08
     Inputs
    -1.95
    输入
    -1.72
     INPUTS
    -1.70
    POSITIVE LOGITS
    StoryboardSegue
    0.76
     desertcart
    0.52
     ArrayAdapter
    0.52
    UnitTesting
    0.52
    providedIn
    0.52
    withIdentifier
    0.50
     errand
    0.49
    featureID
    0.49
     zato
    0.49
     lamella
    0.48
    Activations Density 8.472%

    No Known Activations