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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5705
    Prev
    Next
    INDEX
    Explanations

    characteristics of rap song lyrics and financial crime

    oai_token-act-pair · gemini-2.0-flash

    unique or non-English tokens

    np_token-act-pair-logits · gpt-4o-mini

    Rapper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     purpoſe
    -0.56
     perſon
    -0.52
     houſe
    -0.52
     ioutil
    -0.50
     wastes
    -0.49
     itſelf
    -0.49
     tundra
    -0.49
     cauſe
    -0.49
     Ordem
    -0.48
    bleiben
    -0.48
    POSITIVE LOGITS
    rrggbb
    0.71
    曖昧さ回避
    0.70
     kasarigan
    0.70
     surla
    0.69
    oa̍t
    0.63
    verwijspagina
    0.60
     Walkover
    0.59
    Vidite
    0.59
    ofold
    0.58
    MessageOf
    0.57
    Activations Density 0.500%

    No Known Activations