© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4881
    Prev
    Next
    INDEX
    Explanations

    words ending in "ately", and variations of the word "appropriate" and words similar to "generate"

    oai_token-act-pair · gemini-2.0-flash

    Programming and wine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     nonUne
    -0.58
    sizeCache
    -0.58
    
    -0.56
    iv
    -0.49
    oader
    -0.49
    pr
    -0.47
     مُعرِّف
    -0.47
    <bos>
    -0.46
     organise
    -0.46
    aarrggbb
    -0.45
    POSITIVE LOGITS
     itſelf
    0.96
     myſelf
    0.88
    bibinfo
    0.86
    pausal
    0.83
    </thead>
    0.82
    _
    0.79
    */;
    0.79
     raiſ
    0.77
    bibfield
    0.76
     themſelves
    0.75
    Activations Density 3.160%

    No Known Activations