© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12014
    Prev
    Next
    INDEX
    Explanations

    HTML code related to hiding or excluding elements and the style attribute.

    oai_token-act-pair · gemini-2.0-flash

    none

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.73
     itſelf
    -1.33
     myſelf
    -1.20
     raiſ
    -1.16
     Monfieur
    -1.15
     auffi
    -1.09
     Theſe
    -1.05
     uſed
    -1.02
     Houſe
    -0.99
     houſe
    -0.98
    POSITIVE LOGITS
     
    0.58
      
    0.51
    SequentialGroup
    0.50
    ℎ
    0.50
     ta
    0.49
     j
    0.49
     d
    0.48
     “
    0.47
    stylesheet
    0.47
    <table>
    0.47
    Activations Density 5.106%

    No Known Activations