© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13465
    Prev
    Next
    INDEX
    Explanations

    questions, information and contact requests

    oai_token-act-pair · gemini-2.0-flash

    technical or informative queries

    np_token-act-pair-logits · gpt-4o-mini

    information and questions

    np_max-act-logits · gemini-2.0-flash
    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
     الحره
    -0.62
    ште
    -0.56
    lichkeiten
    -0.55
    Digitized
    -0.53
    abestanden
    -0.53
    SharedCtor
    -0.52
    chik
    -0.52
    globalData
    -0.52
    AGGIO
    -0.51
     points
    -0.51
    POSITIVE LOGITS
     مشين
    0.66
    typeorm
    0.66
    TargetException
    0.66
     femininas
    0.59
     infantiles
    0.59
    mybatisplus
    0.58
    IUrlHelper
    0.57
     présentes
    0.55
    OnAdd
    0.54
     TimeUnit
    0.54
    Activations Density 0.971%

    No Known Activations