© 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. 10375
    Prev
    Next
    INDEX
    Explanations

    words used in discussions of astrophysics

    oai_token-act-pair · gemini-2.0-flash

    astrophysics

    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
    fjspx
    -0.90
    TintMode
    -0.88
    ScopeManager
    -0.86
    IUrlHelper
    -0.77
    CloseOperation
    -0.74
    gbaar
    -0.70
    ftagPool
    -0.70
    WebVitals
    -0.69
    BorderFactory
    -0.69
    itattu
    -0.68
    POSITIVE LOGITS
    urne
    0.43
     seed
    0.42
    bound
    0.41
    She
    0.40
    seed
    0.39
    ervo
    0.39
     inc
    0.38
     She
    0.38
     soğ
    0.37
    ov
    0.36
    Activations Density 2.154%

    No Known Activations