© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4976
    Prev
    Next
    INDEX
    Explanations

    turns of phrase used in spoken dialogue

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IsContent
    -1.23
    évaluateur
    -1.07
    ########.
    -1.05
    IUrlHelper
    -1.05
     незавершена
    -1.05
     تضيفلها
    -1.03
     ujednoznacz
    -0.99
    AndEndTag
    -0.98
    RegressionTest
    -0.98
    TagMode
    -0.98
    POSITIVE LOGITS
     
    0.71
    ↵↵
    0.67
    ↵
    0.61
     The
    0.60
     "
    0.60
     He
    0.59
     he
    0.57
     X
    0.56
     A
    0.54
    ↵↵↵
    0.54
    Activations Density 4.874%

    No Known Activations