© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 723
    Prev
    Next
    INDEX
    Explanations

    relative descriptors and comparisons

    oai_token-act-pair · gemini-2.0-flash

    relatively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     relatively
    -1.27
    relatively
    -1.19
     Relatively
    -1.09
     relativamente
    -1.09
     relativement
    -1.02
     comparatively
    -0.90
     relativ
    -0.86
     fairly
    -0.77
     reasonably
    -0.75
    比較的
    -0.71
    POSITIVE LOGITS
    <bos>
    0.85
    IUrlHelper
    0.74
    tagHelperRunner
    0.69
     ModelExpression
    0.65
    uxxxx
    0.64
    zyści
    0.60
     Савезне
    0.60
     AssemblyCulture
    0.58
    __':
    0.58
    RouterModule
    0.58
    Activations Density 7.944%

    No Known Activations