© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    parentheses, especially those enclosing a number or letter

    oai_token-act-pair · gemini-2.0-flash

    open parenthesis

    np_max-act · gemini-2.0-flash

    ▁(

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     (
    -3.23
     
    -1.39
     A
    -1.12
     [
    -1.12
     I
    -1.05
     -
    -1.02
      
    -1.00
     The
    -0.98
    (
    -0.95
     and
    -0.95
    POSITIVE LOGITS
     myſelf
    2.19
     itſelf
    2.19
     Monfieur
    2.14
     Theſe
    2.05
     ―――――
    1.98
     Anſ
    1.95
     Houſe
    1.93
     Efq
    1.93
     ་་
    1.93
    ſelf
    1.93
    Activations Density 2.995%

    No Known Activations