© 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. 6872
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" used to describe a personal experience or observation

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'sit'

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

    sitting, seated

    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
    EndGlobalSection
    -0.79
    __);
    -0.78
    VIAF
    -0.74
    новниш
    -0.72
    BeginContext
    -0.72
     समीक्षक
    -0.68
     ObjectParameter
    -0.67
     createState
    -0.65
    DoubleQuotes
    -0.64
    SourceChecksum
    -0.64
    POSITIVE LOGITS
     sit
    0.60
     empty
    0.49
     sits
    0.49
     ocupar
    0.49
    newtheorem
    0.45
    sit
    0.44
    empty
    0.44
     float
    0.43
     filling
    0.43
    flo
    0.43
    Activations Density 1.592%

    No Known Activations