© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    legal citations, code snippets, and other non-natural language artifacts

    oai_token-act-pair · gemini-2.0-flash

    emphasis tag

    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
    Negative Logits
    .
    -1.65
    </h5>
    -1.13
    ↵
    -1.08
    </em>
    -1.07
    </i>
    -1.05
    </blockquote>
    -0.98
    ...
    -0.98
    ↵↵↵
    -0.86
    :
    -0.83
    !
    -0.81
    POSITIVE LOGITS
    <bos>
    2.52
     Monfieur
    1.66
     myſelf
    1.59
    ſelf
    1.48
     itſelf
    1.46
    ſelves
    1.45
     Theſe
    1.41
     raiſ
    1.38
     Efq
    1.38
     pleaſure
    1.38
    Activations Density 12.467%

    No Known Activations