© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2657
    Prev
    Next
    INDEX
    Explanations

    the breaks inside scientific papers.

    oai_token-act-pair · gemini-2.0-flash

    non-standard punctuation and coding elements

    np_token-act-pair-logits · gpt-4o-mini

    scientific 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     tuong
    -0.66
     Efq
    -0.64
     BorderRadius
    -0.63
     Савезне
    -0.61
     Nebu
    -0.60
    WindowConstants
    -0.60
     Diſ
    -0.59
     insuffisamment
    -0.57
     Spra
    -0.57
    forChild
    -0.56
    POSITIVE LOGITS
     (
    0.44
    ↵
    0.44
    **********/
    0.43
    rawDesc
    0.40
     future
    0.40
    ValueStyle
    0.39
     typelib
    0.39
    (");
    0.38
     iParam
    0.38
    </code>
    0.37
    Activations Density 3.208%

    No Known Activations