© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12311
    Prev
    Next
    INDEX
    Explanations

    phrases such as "demonstrated by", "reflected in", or "testified by".

    oai_token-act-pair · gemini-2.0-flash

    Showing, proving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     protoimpl
    -0.58
    -------------</
    -0.49
     aasta
    -0.47
    Pa
    -0.45
    P
    -0.45
    createDate
    -0.44
    n
    -0.44
    மாக
    -0.43
     چرا
    -0.43
    N
    -0.43
    POSITIVE LOGITS
     nakalista
    0.81
    NameInMap
    0.71
    findpost
    0.70
    theil
    0.67
     surla
    0.64
    ViewImports
    0.63
    DotNetBar
    0.63
    脚注の使い方
    0.61
    ähteet
    0.60
    ViewInit
    0.60
    Activations Density 0.597%

    No Known Activations