© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14933
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to bodily functions and taking care of babies

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     initComponents
    -1.06
     lenker
    -0.78
    存于互联网档案馆
    -0.73
     autorytatywna
    -0.69
     resourceCulture
    -0.68
     beginnetje
    -0.67
     ISNI
    -0.66
     nahilalakip
    -0.65
    WebElementEntity
    -0.64
     AssemblyTitle
    -0.63
    POSITIVE LOGITS
     становника
    0.72
    ,:);
    0.62
    }:${
    0.57
    )<<
    0.57
    acies
    0.55
     '+':
    0.54
     ':'
    0.54
    ]<<
    0.54
    (),
    
    0.54
    ++;
    
    0.54
    Activations Density 18.040%

    No Known Activations