© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    computer file formats and related verbs.

    oai_token-act-pair · gemini-2.0-flash

    file and data handling

    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
    LookAnd
    -0.63
    SharedCtor
    -0.62
     resourceCulture
    -0.60
     estimés
    -0.60
    awtextra
    -0.58
    RTEE
    -0.58
    []){
    -0.54
    Хьажоргаш
    -0.54
     @"/
    -0.54
    ']))
    -0.53
    POSITIVE LOGITS
    ########.
    0.67
    Externí
    0.66
     chi̍t
    0.53
    eX
    0.51
    renia
    0.49
    Бахар
    0.49
    Shallow
    0.47
    Collegamenti
    0.47
     autorytatywna
    0.47
     aidant
    0.46
    Activations Density 5.805%

    No Known Activations