© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    the root 'repeat' and words and phrases in the context of rules or repeated events

    oai_token-act-pair · gemini-2.0-flash

    repeat

    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
     itſelf
    -1.98
     myſelf
    -1.82
     ―――――
    -1.75
     Monfieur
    -1.62
     ་་
    -1.60
     Anſ
    -1.60
     Theſe
    -1.60
     Efq
    -1.59
     ainfi
    -1.56
     Houſe
    -1.55
    POSITIVE LOGITS
    ↵↵
    0.99
    .
    0.98
    <eos>
    0.98
    :
    0.82
    ?
    0.77
     
    0.77
     -
    0.77
    y
    0.76
     l
    0.74
    ..
    0.74
    Activations Density 2.345%

    No Known Activations