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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10390
    Prev
    Next
    INDEX
    Explanations

    lists of ingredients and conjunctions used in recipes

    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
    MethodManager
    -0.59
    NSUserDefaults
    -0.51
     dago
    -0.50
     onAnimation
    -0.49
     moschino
    -0.49
    FormTagHelper
    -0.48
     Hitam
    -0.48
     Partagez
    -0.47
    Према
    -0.46
    Initializable
    -0.46
    POSITIVE LOGITS
    KommentareTeilen
    0.61
    ⓘ
    0.59
    ⎨
    0.59
    #+#
    0.58
    <bos>
    0.57
     autorytatywna
    0.55
     soy
    0.54
     Вікі
    0.54
     jScrollPane
    0.51
     Generales
    0.51
    Activations Density 0.920%

    No Known Activations