© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    html tags, especially related to forms and radio buttons and also finds the word "object."

    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
     Kinds
    -1.18
     kinds
    -1.14
    kinds
    -1.13
     types
    -1.06
     sorts
    -1.03
     sort
    -1.02
    kind
    -1.02
     Types
    -1.01
    types
    -1.01
    Types
    -1.01
    POSITIVE LOGITS
     découver
    0.58
    rungsseite
    0.53
    NameInMap
    0.49
    JsonInclude
    0.48
    Tcp
    0.46
     NUKAT
    0.46
    datatables
    0.45
     Thy
    0.45
     télévis
    0.43
    تی
    0.42
    Activations Density 2.585%

    No Known Activations