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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1191
    Prev
    Next
    INDEX
    Explanations

    lines of rap lyrics exhibiting a high frequency of single character tokens

    oai_token-act-pair · gemini-2.0-flash

    Rap lyrics

    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
    ,
    -0.52
     el
    -0.42
     g
    -0.38
    ;
    -0.36
     ked
    -0.36
     ONE
    -0.35
     il
    -0.34
    :
    -0.34
     sa
    -0.34
    ',
    -0.34
    POSITIVE LOGITS
     itſelf
    1.08
    IUrlHelper
    1.03
    ſelf
    1.02
     ་་
    0.98
    oredCriteria
    0.97
     uſed
    0.96
     ―――――
    0.94
     CreateTagHelper
    0.94
    ſelves
    0.93
     $_"
    0.93
    Activations Density 10.326%

    No Known Activations