© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4281
    Prev
    Next
    INDEX
    Explanations

    text describing the combination of multiple things, especially when referring to the itertools module in Python

    oai_token-act-pair · gemini-2.0-flash

    combination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    tvguidetime
    -0.81
    AndEndTag
    -0.73
     يتيمه
    -0.71
     الحره
    -0.69
     
    -0.69
    ENOMEM
    -0.61
     InputDecoration
    -0.59
    Bism
    -0.59
     EconPapers
    -0.58
    Personendaten
    -0.58
    POSITIVE LOGITS
    SetItem
    0.48
     BoxFit
    0.46
     diligen
    0.46
     trưởng
    0.45
    起来
    0.43
    Válasz
    0.42
     Meredith
    0.42
     sẵn
    0.42
     Beecher
    0.41
    ViewChild
    0.41
    Activations Density 1.109%

    No Known Activations