© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    phrases containing words like "constant" and "relatively"

    oai_token-act-pair · gemini-2.0-flash

    constant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pleinement
    -0.57
    heça
    -0.56
     pouvoit
    -0.55
    مجموع
    -0.53
     Tenga
    -0.53
     giovan
    -0.52
     rempliss
    -0.52
     îna
    -0.51
     propOrder
    -0.51
    riwal
    -0.51
    POSITIVE LOGITS
     useState
    0.69
    EDEFAULT
    0.63
     unchanging
    0.57
    msgTypes
    0.55
    Xna
    0.54
    UnifiedTopology
    0.54
    useState
    0.54
    fony
    0.54
     homeowner
    0.54
    tanleria
    0.53
    Activations Density 1.435%

    No Known Activations