© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9840
    Prev
    Next
    INDEX
    Explanations

    words related to study locations and contexts

    oai_token-act-pair · gemini-2.0-flash

    prevalence rates in specific populations

    np_token-act-pair-logits · gpt-4o-mini
    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
    发表于
    -0.62
    ValueStyle
    -0.60
    }`).
    -0.57
    UnknownFields
    -0.55
     يتيمه
    -0.55
    contentLoaded
    -0.55
     NavController
    -0.54
     Réponses
    -0.52
    élie
    -0.52
    izop
    -0.52
    POSITIVE LOGITS
    jmniej
    0.46
    olito
    0.45
     Guilt
    0.44
     بدر
    0.44
    Cres
    0.44
    EndContext
    0.43
     nakalista
    0.43
     volley
    0.43
    Something
    0.43
    ιώ
    0.42
    Activations Density 1.035%

    No Known Activations