© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12585
    Prev
    Next
    INDEX
    Explanations

    text describing emotional and physical suffering

    oai_token-act-pair · gemini-2.0-flash

    words associated with negative emotional states

    np_token-act-pair-logits · gpt-4o-mini

    negative feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    menuStrip
    -0.62
    GOTREF
    -0.59
    FunctionFlags
    -0.57
     فريبيس
    -0.57
     ressemb
    -0.56
     يتيمه
    -0.56
    wechs
    -0.56
    +:+
    -0.56
    tabilidade
    -0.55
    mariage
    -0.55
    POSITIVE LOGITS
     stressed
    0.59
    enumi
    0.55
     fed
    0.54
    onAttach
    0.51
     sick
    0.50
     anxious
    0.50
    InjectAttribute
    0.49
     fatigued
    0.49
     sensi
    0.49
     tired
    0.48
    Activations Density 0.726%

    No Known Activations