© 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. 3923
    Prev
    Next
    INDEX
    Explanations

    information about finding something out or places to find things, especially regarding creative works

    oai_token-act-pair · gemini-2.0-flash

    Web page excerpts

    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
     myſelf
    -0.94
     itſelf
    -0.88
     themſelves
    -0.87
     ſeveral
    -0.86
     himſelf
    -0.85
     Theſe
    -0.85
     whoſe
    -0.82
     ſche
    -0.82
    Portály
    -0.79
     leaſt
    -0.77
    POSITIVE LOGITS
     ».
    0.65
     »
    0.65
     at
    0.63
    »
    0.59
     =>
    0.59
     >
    0.57
    ».
    0.55
    >
    0.54
     PyTuple
    0.54
     ->
    0.51
    Activations Density 10.374%

    No Known Activations