© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14271
    Prev
    Next
    INDEX
    Explanations

    words that are used in the french language

    oai_token-act-pair · gemini-2.0-flash

    non-English text 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
    LoggerFactory
    -0.51
     Giuliano
    -0.51
     Ons
    -0.49
    ApiModelProperty
    -0.49
    anti
    -0.49
     ili
    -0.47
    ContentAsync
    -0.47
    uš
    -0.45
    jspx
    -0.44
    ForRow
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.68
     Мексичка
    0.63
     varandra
    0.59
    CppMethod
    0.58
    __':
    0.57
     cucchiai
    0.57
    othes
    0.57
     >=",
    0.57
    پیوند
    0.56
     personnalité
    0.56
    Activations Density 0.702%

    No Known Activations