© 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. 6637
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business, websites, and professional services.

    oai_token-act-pair · gemini-2.0-flash

    words related to formal processes or classifications

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

    period

    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
     ProtoMessage
    -0.94
    aarrggbb
    -0.88
     Normdatei
    -0.84
    IsContent
    -0.83
     arşivlendi
    -0.75
    esModule
    -0.74
    AndEndTag
    -0.71
     snippetHide
    -0.70
     bit
    -0.70
     ویکی‌پدیای
    -0.65
    POSITIVE LOGITS
    initialise
    0.70
    labour
    0.59
    ategorised
    0.59
     randomised
    0.59
     labour
    0.59
    Analyse
    0.59
    personalised
    0.59
     initialise
    0.57
    authorised
    0.57
    organised
    0.55
    Activations Density 2.765%

    No Known Activations