© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9314
    Prev
    Next
    INDEX
    Explanations

    dates, numbers within dates, and colons.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -1.27
     raiſ
    -1.24
     Efq
    -1.19
     itſelf
    -1.19
     purpoſe
    -1.16
    TagMode
    -1.13
     pleaſure
    -1.09
     Houſe
    -1.08
     ſche
    -1.07
     ―――――
    -1.05
    POSITIVE LOGITS
    ↵
    0.66
     
    0.65
    ...
    0.65
    /
    0.60
    <eos>
    0.57
    </strong>
    0.57
     Je
    0.56
     Chi
    0.55
     Central
    0.53
     #
    0.52
    Activations Density 6.260%

    No Known Activations