© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    code-related texts or technical documentation

    oai_token-act-pair · gemini-2.0-flash

    software applications

    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
     stack
    -0.53
    stack
    -0.49
     OS
    -0.48
     noDo
    -0.47
    [--
    -0.45
    Usos
    -0.43
    Stack
    -0.43
     Westbrook
    -0.43
    jspb
    -0.43
     Radcliffe
    -0.42
    POSITIVE LOGITS
     AssemblyTitle
    0.73
    xffffff
    0.68
     صوتيه
    0.67
     protoimpl
    0.66
    WriteTagHelper
    0.66
     تضيفلها
    0.65
    IntoConstraints
    0.65
     programmers
    0.63
     GenerationType
    0.63
    expandindo
    0.63
    Activations Density 12.389%

    No Known Activations