© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    words related to suffering and medical or psychological intervention for it

    oai_token-act-pair · gemini-2.0-flash

    Pain/stress

    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
    onOptions
    -0.62
    >(),
    -0.56
    nativeElement
    -0.54
    CodedInputStream
    -0.52
    maketitle
    -0.52
    :^(
    -0.50
    CodeAttribute
    -0.50
    PAREN
    -0.49
     Kon
    -0.49
    AddWithValue
    -0.47
    POSITIVE LOGITS
    szt
    0.54
     مواليد
    0.52
     BorderRadius
    0.52
     незавершена
    0.51
     centers
    0.49
     Commencez
    0.49
    UserScript
    0.49
    SPJ
    0.47
    esez
    0.46
    eraard
    0.46
    Activations Density 5.117%

    No Known Activations