© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10098
    Prev
    Next
    INDEX
    Explanations

    words used to communicate results in a competitive setting

    oai_token-act-pair · gemini-2.0-flash

    Near, not open

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    허
    -0.66
    CppMethod
    -0.64
    LEncoder
    -0.64
     referenties
    -0.55
    PyExc
    -0.53
     متعلقه
    -0.53
    帖最后由
    -0.53
    CDCl
    -0.52
    Kaynakça
    -0.52
    Portály
    -0.52
    POSITIVE LOGITS
     close
    1.04
     Close
    0.81
     tight
    0.80
    close
    0.79
     CLOSE
    0.76
    Close
    0.74
    CLOSE
    0.69
    tight
    0.66
     tough
    0.63
    ंदीखरीदारी
    0.63
    Activations Density 3.174%

    No Known Activations