© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9905
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatment and individualized patient care

    oai_token-act-pair · gemini-2.0-flash

    Individual

    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
     kasarigan
    -0.70
     ligiloj
    -0.69
    ंदीखरीदारी
    -0.68
    contentLoaded
    -0.63
     بيها
    -0.59
    frastructure
    -0.58
    Véxase
    -0.57
    Viited
    -0.56
    duled
    -0.53
    inSlope
    -0.51
    POSITIVE LOGITS
     individual
    2.56
    Individual
    2.44
     Individual
    2.41
    individual
    2.41
     individually
    2.20
     INDIVIDUAL
    2.16
     Individ
    2.06
     individ
    2.03
    Individ
    1.99
    individ
    1.95
    Activations Density 3.205%

    No Known Activations