© 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. 10935
    Prev
    Next
    INDEX
    Explanations

    the word "mode"

    oai_token-act-pair · gemini-2.0-flash

    mode

    np_max-act · gemini-2.0-flash

    mode

    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
    ,
    -2.58
    .
    -2.17
     (
    -1.98
    -
    -1.91
    /
    -1.79
     
    -1.77
    ;
    -1.69
     in
    -1.65
    :
    -1.63
     M
    -1.62
    POSITIVE LOGITS
     myſelf
    4.56
     Efq
    4.34
     Monfieur
    4.25
     itſelf
    4.22
     Theſe
    4.16
     Jefus
    3.95
     themſelves
    3.94
     purpoſe
    3.91
     Majefty
    3.84
     ſeveral
    3.81
    Activations Density 1.238%

    No Known Activations