© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    words related to academic studies and research

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "model"

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

    model

    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
     insuffisamment
    -0.89
     تانيه
    -0.75
     Efq
    -0.72
     Theſe
    -0.72
    RenderAtEndOf
    -0.71
    SharedDtor
    -0.68
     ―――――
    -0.65
     myſelf
    -0.61
     snippetHide
    -0.61
     חיצוניים
    -0.61
    POSITIVE LOGITS
     model
    0.74
    model
    0.54
    Model
    0.53
     models
    0.51
     Model
    0.51
    zydent
    0.50
     modello
    0.50
     factor
    0.48
     tax
    0.48
     MODEL
    0.47
    Activations Density 4.683%

    No Known Activations