© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    words or short phrases in a variety of languages, including code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code/technical text

    np_max-act-logits · gemini-2.0-flash

    ▁ (space-prefix)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     
    -0.64
    ↵↵
    -0.55
    ↵
    -0.54
    <eos>
    -0.53
     i
    -0.52
     (
    -0.45
    .
    -0.40
     I
    -0.40
     l
    -0.40
    ,
    -0.39
    POSITIVE LOGITS
     myſelf
    2.39
     Efq
    2.36
     Monfieur
    2.30
     Theſe
    2.19
     itſelf
    2.17
    ſelf
    2.09
     Majefty
    2.08
     ―――――
    2.06
     pleaſure
    2.06
     himſelf
    2.05
    Activations Density 2.254%

    No Known Activations