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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10391
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to pain and childbirth

    oai_token-act-pair · gemini-2.0-flash

    pain and discomfort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TagHelper
    -0.64
    ();)
    -0.56
    CompoundButton
    -0.52
    MENAFN
    -0.51
    esez
    -0.51
    Multipart
    -0.51
    Gemeinsame
    -0.50
    SystemColors
    -0.49
    MemoryWarning
    -0.48
    łąd
    -0.48
    POSITIVE LOGITS
     Infórmanos
    0.59
    الحياه
    0.58
    cloudfront
    0.54
    eturn
    0.53
     للمعارف
    0.52
    wahati
    0.50
     utafitiHapana
    0.48
     nakalista
    0.47
    RUnlock
    0.46
     AspNetCore
    0.46
    Activations Density 2.425%

    No Known Activations