© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15313
    Prev
    Next
    INDEX
    Explanations

    descriptions of plants, particularly their physical characteristics like size, color, and shape.

    oai_token-act-pair · gemini-2.0-flash

    code and technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     intento
    -0.53
     missione
    -0.51
     représentants
    -0.49
     tentativo
    -0.46
     partenza
    -0.46
     frequenza
    -0.46
     igenom
    -0.44
     scolaires
    -0.43
     benzina
    -0.43
     minggu
    -0.43
    POSITIVE LOGITS
    addCriterion
    0.73
    WebServlet
    0.68
    .}~\
    0.68
     setCode
    0.66
    Coordenadas
    0.65
    writeField
    0.64
    setDo
    0.63
    ResumeLayout
    0.62
    exitRule
    0.62
    ]**
    0.61
    Activations Density 20.875%

    No Known Activations