© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11511
    Prev
    Next
    INDEX
    Explanations

    scientific descriptions of experimental results

    oai_token-act-pair · gemini-2.0-flash

    described

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     described
    -1.35
     mentioned
    -1.31
    described
    -1.22
     discussed
    -1.09
    mentioned
    -1.08
    discussed
    -0.97
     descrito
    -0.97
     mencionados
    -0.94
     mencionado
    -0.94
     outlined
    -0.94
    POSITIVE LOGITS
     surla
    0.68
     Савезне
    0.66
    исленность
    0.61
    <bos>
    0.60
    RRect
    0.57
    ########.
    0.56
    Autoritní
    0.55
    ogaster
    0.54
    niająca
    0.54
     CURIAM
    0.54
    Activations Density 2.761%

    No Known Activations