© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12685
    Prev
    Next
    INDEX
    Explanations

    the word "default"

    oai_token-act-pair · gemini-2.0-flash

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     default
    -2.97
    default
    -2.56
     Default
    -2.31
    Default
    -2.19
     defaults
    -1.80
    默认
    -1.73
     defaulted
    -1.66
    DEFAULT
    -1.59
     DEFAULT
    -1.59
    デフォ
    -1.44
    POSITIVE LOGITS
     Paglinawan
    0.49
    gub
    0.43
     justiça
    0.43
     particulières
    0.43
    motiv
    0.43
    afficheront
    0.42
     thước
    0.42
    Getter
    0.42
     бъде
    0.41
     recevez
    0.41
    Activations Density 0.782%

    No Known Activations