© 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. 10656
    Prev
    Next
    INDEX
    Explanations

    interrogative words

    oai_token-act-pair · gemini-2.0-flash

    how/nor

    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
     do
    -1.06
     Do
    -1.05
    Do
    -1.00
     DO
    -0.81
    do
    -0.81
     duquel
    -0.64
     Shall
    -0.64
     Did
    -0.63
    TagMode
    -0.63
    quelize
    -0.62
    POSITIVE LOGITS
     is
    0.60
     المعيارى
    0.52
     does
    0.49
     viewDidLoad
    0.48
    RegressionTest
    0.47
     utafitiHapana
    0.46
    SharedCtor
    0.40
    ٔ
    0.40
     му
    0.39
     riten
    0.39
    Activations Density 0.775%

    No Known Activations