© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15193
    Prev
    Next
    INDEX
    Explanations

    acronyms for organizations as well as football clubs

    oai_token-act-pair · gemini-2.0-flash

    uncommon language and formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     насељу
    -0.41
    \{\\
    -0.40
    endforeach
    -0.37
    ->
    -0.35
    onSave
    -0.34
    liel
    -0.33
    hoho
    -0.33
     Allen
    -0.33
    gration
    -0.33
    RTLR
    -0.33
    POSITIVE LOGITS
     ſch
    0.80
    ſelves
    0.77
     AssemblyTitle
    0.74
    //});
    0.73
     pleaſure
    0.73
     ſen
    0.72
     Sandi
    0.71
    GEBURTSDATUM
    0.69
     ―――――
    0.69
     Diſ
    0.68
    Activations Density 0.246%

    No Known Activations