© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    people talking about things they enjoy, like food, books, and hobbies

    oai_token-act-pair · gemini-2.0-flash

    enjoy

    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
     Efq
    -2.31
     myſelf
    -2.28
     ―――――
    -2.23
     itſelf
    -2.22
    ^(@)
    -2.22
     Jefus
    -2.17
     doubtnut
    -2.11
     resourceCulture
    -2.08
     Theſe
    -2.08
     ་་
    -2.05
    POSITIVE LOGITS
    1
    1.47
    ↵
    1.36
    ↵↵
    1.34
    2
    1.33
     
    1.32
    3
    1.30
    4
    1.27
    <eos>
    1.23
    5
    1.23
    0
    1.20
    Activations Density 2.170%

    No Known Activations