© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4849
    Prev
    Next
    INDEX
    Explanations

    what appears to be poorly formatted or commented code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     PyLong
    -0.61
    niająca
    -0.58
    RTEX
    -0.58
    EndGlobalSection
    -0.58
    Abit
    -0.58
    oredCriteria
    -0.54
    webElementXpaths
    -0.54
     protoimpl
    -0.53
    AddField
    -0.53
    engelsk
    -0.52
    POSITIVE LOGITS
    BindingResult
    0.61
    newArrayList
    0.52
     يتيمه
    0.52
    <?>>
    0.52
    acquired
    0.51
     للمعارف
    0.49
     Thee
    0.48
     koncert
    0.48
    DialogInterface
    0.47
    freiheit
    0.47
    Activations Density 3.778%

    No Known Activations