© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10096
    Prev
    Next
    INDEX
    Explanations

    text containing mathematical formulas within a scientific document

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     snippetHide
    -0.54
    Lähteet
    -0.54
     voork
    -0.53
    GenerationType
    -0.52
     nakalista
    -0.52
    DoubleQuotes
    -0.51
    Viited
    -0.50
    ❋
    -0.50
    kháu
    -0.50
     titolata
    -0.50
    POSITIVE LOGITS
     GetEnumerator
    0.64
    +#+#
    0.53
     coma
    0.52
    WebControls
    0.51
    BufferException
    0.50
     ca
    0.49
    WriteBarrier
    0.48
     ~
    0.48
    日まで
    0.48
    omeness
    0.46
    Activations Density 7.466%

    No Known Activations