© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10400
    Prev
    Next
    INDEX
    Explanations

    single digits, numbers and number-related scientific measurement abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    words related to numeric data or measurements

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

    molecular biology contexts

    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
     Monfieur
    -0.76
    withIdentifier
    -0.71
     dépens
    -0.70
    ########.
    -0.69
     myſelf
    -0.69
     spørs
    -0.69
     morocco
    -0.69
     themſelves
    -0.68
     "..\..\
    -0.68
     navnet
    -0.68
    POSITIVE LOGITS
     sie
    0.52
    بوابة
    0.50
      
    0.50
    MemoryWarning
    0.47
     Bra
    0.46
    Бахар
    0.44
    Portale
    0.43
     كومونز
    0.43
     ra
    0.42
     am
    0.42
    Activations Density 4.893%

    No Known Activations