© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4504
    Prev
    Next
    INDEX
    Explanations

    blocks of programming code

    oai_token-act-pair · 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
    ">//
    -0.76
    TypedDataSet
    -0.69
    出版年
    -0.69
     transfieras
    -0.69
     Савезне
    -0.69
     ProtoMessage
    -0.66
    InvalidProtocol
    -0.64
    LabelTagHelper
    -0.63
    XmlAccessType
    -0.62
     esternos
    -0.61
    POSITIVE LOGITS
                                
    0.52
    hman
    0.50
    hlo
    0.47
     disponibilités
    0.46
    hl
    0.45
    %")
    0.45
    herty
    0.43
    المناصب
    0.43
    wór
    0.41
    mannian
    0.41
    Activations Density 0.120%

    No Known Activations