© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6360
    Prev
    Next
    INDEX
    Explanations

    the letters "y" followed by two letters, especially in the context of group

    oai_token-act-pair · gemini-2.0-flash

    French words or terms

    np_token-act-pair-logits · gpt-4o-mini

    academic publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Taktlose
    -0.68
    ArgsConstructor
    -0.63
     snippetHide
    -0.62
    PerformLayout
    -0.61
    ChildScrollView
    -0.59
    AnchorStyles
    -0.59
     الرياضيه
    -0.59
     Wikispecies
    -0.56
    Javadoc
    -0.56
     {?}
    -0.56
    POSITIVE LOGITS
     blessés
    0.50
     humains
    0.50
     Bergh
    0.49
     nisso
    0.48
     embuti
    0.48
     actuelles
    0.47
     sedih
    0.45
     vectorielle
    0.45
     thảm
    0.45
     Funktion
    0.45
    Activations Density 0.074%

    No Known Activations