© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4658
    Prev
    Next
    INDEX
    Explanations

    words related to children and anxiety

    oai_token-act-pair · gemini-2.0-flash

    debate/discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    نگار
    -0.51
     impl
    -0.48
    prits
    -0.47
     proven
    -0.44
    ั่ง
    -0.44
     favorable
    -0.44
     näher
    -0.44
    Compatible
    -0.44
     reger
    -0.43
    ILIO
    -0.43
    POSITIVE LOGITS
    InjectAttribute
    0.66
     propOrder
    0.66
    ContentAsync
    0.65
    kháu
    0.60
    onAttach
    0.59
     برانيه
    0.58
    SupportActionBar
    0.57
    لسط
    0.56
     Exactos
    0.56
    ]='\
    0.54
    Activations Density 9.380%

    No Known Activations