© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14971
    Prev
    Next
    INDEX
    Explanations

    code or markdown-like formatting

    oai_token-act-pair · gemini-2.0-flash

    code and identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    4
    -1.52
     four
    -1.19
     Four
    -1.02
    ４
    -0.91
    four
    -0.89
     vier
    -0.89
     cuatro
    -0.89
     keempat
    -0.89
     FOUR
    -0.89
     четыре
    -0.86
    POSITIVE LOGITS
     Bourgoin
    0.63
    Rhestr
    0.52
     bezeichneter
    0.52
    fromnode
    0.52
     StatefulWidget
    0.50
    UIControlState
    0.50
    sizeCache
    0.48
     trois
    0.47
    autoreleasepool
    0.47
     viewDidLoad
    0.46
    Activations Density 0.891%

    No Known Activations