© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15496
    Prev
    Next
    INDEX
    Explanations

    phrases describing movement from one thing to another.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    awtextra
    -0.66
     áp
    -0.52
    ButterKnife
    -0.52
    {#
    -0.50
    idens
    -0.50
    ⁢
    -0.48
    noinspection
    -0.48
    ‍
    -0.48
    sinon
    -0.47
    TIMORE
    -0.47
    POSITIVE LOGITS
     mergeFrom
    0.71
     magasiner
    0.61
    ])->
    0.59
     دیکھیے
    0.59
    msgTypes
    0.58
     '\\;'
    0.56
     pinulongan
    0.56
    #+#
    0.56
    \}\\
    0.56
    colgroup
    0.55
    Activations Density 3.046%

    No Known Activations