© 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. 9712
    Prev
    Next
    INDEX
    Explanations

    words related to counting, selection, and procedures involving multiple steps.

    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
    DebuggerNonUser
    -0.66
    NameInMap
    -0.65
     snippetHide
    -0.65
     onCancelled
    -0.64
    MENAFN
    -0.63
    BeginContext
    -0.62
     Мексичка
    -0.61
    ."));
    -0.61
    getColumnIndex
    -0.60
     PhpStorm
    -0.60
    POSITIVE LOGITS
     ar
    1.34
     arc
    1.20
     а
    1.00
     aro
    0.98
     ab
    0.97
     ate
    0.95
     al
    0.94
     ara
    0.91
     ah
    0.87
    arc
    0.86
    Activations Density 5.329%

    No Known Activations