© 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. 5198
    Prev
    Next
    INDEX
    Explanations

    words related to conversation, discussion, and telling

    oai_token-act-pair · gemini-2.0-flash

    about

    np_max-act-logits · gemini-2.0-flash

    discussions about various topics

    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
    for
    -0.48
    we
    -0.48
    with
    -0.45
     он
    -0.42
    about
    -0.40
    打
    -0.40
     hän
    -0.40
    We
    -0.40
    mas
    -0.40
     tepat
    -0.40
    POSITIVE LOGITS
     how
    1.21
    sizeCache
    1.02
     '\\;'
    0.98
    DockStyle
    0.98
    AddTagHelper
    0.92
    Autoritní
    0.90
     mergeFrom
    0.90
     themſelves
    0.88
     whoſe
    0.88
     what
    0.87
    Activations Density 5.277%

    No Known Activations