© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 732
    Prev
    Next
    INDEX
    Explanations

    passages from old books and plays

    oai_token-act-pair · 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
     uintptr
    -0.33
     ga
    -0.33
     DIV
    -0.32
     RoutedEventArgs
    -0.32
     iArr
    -0.30
     Div
    -0.29
    вни
    -0.29
    口
    -0.29
     onAnimation
    -0.28
     va
    -0.28
    POSITIVE LOGITS
     Jefus
    1.22
     Monfieur
    1.20
     whoſe
    1.20
     myſelf
    1.20
     Efq
    1.18
     becauſe
    1.16
     Theſe
    1.13
     purpoſe
    1.13
     pleaſure
    1.13
     himſelf
    1.13
    Activations Density 3.128%

    No Known Activations