© 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. 12266
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with psychological trauma and PTSD

    oai_token-act-pair · gemini-2.0-flash

    the term 'post'

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

    stress and trauma

    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
    تقاوى
    -0.62
    ValueStyle
    -0.61
     esternos
    -0.58
    himovic
    -0.58
    Autoritní
    -0.57
    convergence
    -0.57
    ScopeManager
    -0.56
    RegistryLite
    -0.56
    kkelijk
    -0.56
    LookAnd
    -0.56
    POSITIVE LOGITS
    mapStateToProps
    0.59
    bolista
    0.56
     post
    0.54
    post
    0.50
     }}"></
    0.48
    Post
    0.48
    stral
    0.47
     dealing
    0.46
    HEL
    0.46
     Post
    0.45
    Activations Density 1.758%

    No Known Activations