© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11695
    Prev
    Next
    INDEX
    Explanations

    information about patents and corporate foundings

    oai_token-act-pair · gemini-2.0-flash

    Patent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Japanese
    -0.76
     Japan
    -0.66
     Iw
    -0.65
     shogun
    -0.64
     Tok
    -0.63
    Japanese
    -0.63
     Fuji
    -0.62
     Mits
    -0.62
     japanese
    -0.60
     Fuk
    -0.59
    POSITIVE LOGITS
    derry
    0.54
     виправивши
    0.52
    setVerticalGroup
    0.50
     bezeichneter
    0.50
    KURZBESCHREIBUNG
    0.49
     facie
    0.48
    writeField
    0.47
    formik
    0.46
    GenerationType
    0.46
    erover
    0.45
    Activations Density 0.465%

    No Known Activations