© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    words related to how things are positioned in a series, or in relation to one another

    oai_token-act-pair · gemini-2.0-flash

    others

    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
    AutoresizingMask
    -0.74
    providedIn
    -0.73
    bibinfo
    -0.71
    undrum
    -0.70
     asegur
    -0.61
    <bos>
    -0.59
    mesis
    -0.58
     beyond
    -0.58
    etCode
    -0.58
    Rujukan
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
     ModelExpression
    0.57
     polie
    0.54
     besonderes
    0.53
    Others
    0.52
    ำ
    0.52
    ])).
    0.51
    others
    0.51
     Specially
    0.49
     собою
    0.49
    Activations Density 1.519%

    No Known Activations