© 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. 12297
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "AT", often followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'At' in various contexts

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

    AT

    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
    WebElementEntity
    -0.69
    存于互联网档案馆
    -0.68
    /*
    -0.63
    WithIOException
    -0.63
    protoc
    -0.63
    ITERATURE
    -0.62
     unknownFields
    -0.62
    sives
    -0.61
    Portail
    -0.60
    bcryptjs
    -0.60
    POSITIVE LOGITS
    #+#
    0.64
    oczes
    0.49
    lante
    0.44
    gento
    0.44
    libft
    0.43
    RequestMapping
    0.42
    renia
    0.42
     what
    0.42
     home
    0.41
    transQ
    0.41
    Activations Density 0.584%

    No Known Activations