© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6914
    Prev
    Next
    INDEX
    Explanations

    words relating to dates and times

    oai_token-act-pair · gemini-2.0-flash

    Time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SdkVersion
    -0.57
    hæng
    -0.52
    телно
    -0.49
    quiel
    -0.48
     Monark
    -0.47
    دانشنامهٔ
    -0.47
     suspendu
    -0.47
     puissante
    -0.47
    quias
    -0.46
    innung
    -0.46
    POSITIVE LOGITS
     during
    1.35
     DURING
    1.20
    during
    1.19
     early
    1.14
     before
    1.11
     durante
    1.06
     During
    1.05
    During
    1.04
     tijdens
    0.99
     BEFORE
    0.98
    Activations Density 6.558%

    No Known Activations