© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3305
    Prev
    Next
    INDEX
    Explanations

    language related to government finances

    oai_token-act-pair · gemini-2.0-flash

    finance and budget

    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
     contextLoads
    -0.87
    tagHelperRunner
    -0.79
     protoimpl
    -0.78
    клопе
    -0.74
    ScopeManager
    -0.74
     насељу
    -0.73
    GraphicsUnit
    -0.72
     nahilalakip
    -0.70
    EndContext
    -0.69
     iprot
    -0.68
    POSITIVE LOGITS
    ad
    0.45
     pompe
    0.43
     bombe
    0.43
    ͍
    0.42
    de
    0.42
     pump
    0.42
    ät
    0.42
     bombas
    0.41
     fede
    0.41
     proyec
    0.41
    Activations Density 1.547%

    No Known Activations