© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9452
    Prev
    Next
    INDEX
    Explanations

    numbers, typically those greater than 1000

    oai_token-act-pair · gemini-2.0-flash

    zero

    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
    -2.02
     Efq
    -2.02
     photolibrary
    -2.00
     ་་
    -1.99
     ―――――
    -1.98
     doubtnut
    -1.94
    ^(@)
    -1.93
     myſelf
    -1.90
     iſt
    -1.89
     Majefty
    -1.87
    POSITIVE LOGITS
    ↵↵
    1.68
     
    1.61
    <eos>
    1.59
    '
    1.59
    ↵
    1.36
    .
    1.35
    ’
    1.33
    ,
    1.28
     and
    1.23
     (
    1.18
    Activations Density 0.352%

    No Known Activations