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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2715
    Prev
    Next
    INDEX
    Explanations

    words or phrases used in technical documents relating to scientific, engineering, and medical contexts, possibly identifying definitions, or directional statements.

    oai_token-act-pair · gemini-2.0-flash

    variations of direct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -0.98
    Autoritní
    -0.63
    RUnlock
    -0.61
     autorytatywna
    -0.59
    PerformLayout
    -0.57
    󠁣
    -0.57
     الاطلاع
    -0.56
    AnchorStyles
    -0.56
    ValueGenerated
    -0.55
    richTextPanel
    -0.55
    POSITIVE LOGITS
     direct
    3.42
    direct
    3.13
     Direct
    3.06
    Direct
    2.83
    DIRECT
    2.31
     DIRECT
    2.28
     directe
    2.09
     directo
    1.94
     directa
    1.82
     directos
    1.81
    Activations Density 5.108%

    No Known Activations