© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6050
    Prev
    Next
    INDEX
    Explanations

    words related to emotions, feelings, injuries, and remedies

    oai_token-act-pair · gemini-2.0-flash

    comfort, relief

    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
    ודם
    -0.50
     tú
    -0.50
     rechange
    -0.50
    excited
    -0.46
    pim
    -0.45
    TAG
    -0.45
     emel
    -0.44
     acredit
    -0.43
    idon
    -0.43
    ÁT
    -0.43
    POSITIVE LOGITS
     comfort
    1.41
     comforts
    1.20
     Comfort
    1.14
    comfort
    1.13
     comforting
    1.12
     solace
    1.09
    Comfort
    1.06
     comforted
    1.05
     consolation
    1.04
     COMFORT
    1.04
    Activations Density 0.918%

    No Known Activations