© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8388
    Prev
    Next
    INDEX
    Explanations

    c code and openCV code, especially function calls and pointer usage

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     sguardo
    -0.56
     estekak
    -0.51
    resizingMask
    -0.49
     referenties
    -0.49
    get
    -0.48
    mapStateToProps
    -0.47
    кои
    -0.47
     păr
    -0.46
    fiez
    -0.44
    down
    -0.44
    POSITIVE LOGITS
    XmlAccessType
    0.66
     ProtoMessage
    0.62
    WriteBarrier
    0.61
    adaptiveStyles
    0.59
    httphttps
    0.59
     InputDecoration
    0.57
    :✨
    0.56
    twimg
    0.55
     JpaRepository
    0.54
     GenerationType
    0.53
    Activations Density 0.303%

    No Known Activations