© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1095
    Prev
    Next
    INDEX
    Explanations

    instances of knowing, thinking, or believing

    oai_token-act-pair · gemini-2.0-flash

    knew/know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    래
    -0.49
     spokes
    -0.47
     giác
    -0.43
     EconPapers
    -0.42
     mais
    -0.41
     تواند
    -0.40
    mistic
    -0.39
    dow
    -0.38
    TotalCount
    -0.38
     folgte
    -0.38
    POSITIVE LOGITS
    ]")]
    0.75
    #+#
    0.60
    AlterField
    0.60
     ویکی‌پدیای
    0.60
     '\\;'
    0.58
     autorytatywna
    0.58
    arakhand
    0.57
     anzuzeigen
    0.56
     FetchType
    0.56
     theſe
    0.56
    Activations Density 0.857%

    No Known Activations