© 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. 4456
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially when they contain escape characters, unicode references, and possibly non-english characters

    oai_token-act-pair · gemini-2.0-flash

    unusual characters

    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
    <eos>
    -0.19
    ↵
    -0.14
    ↵↵
    -0.08
    i
    -0.08
    x
    -0.08
    -0.07
    1
    -0.07
    to
    -0.06
    k
    -0.06
    with
    -0.06
    POSITIVE LOGITS
     Efq
    1.91
     ―――――
    1.86
     itſelf
    1.85
    ^(@)
    1.84
     ་་
    1.79
     myſelf
    1.79
    ſelf
    1.75
    ſelves
    1.71
     iſt
    1.70
     Monfieur
    1.68
    Activations Density 34.598%
    No Known Activations