© 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. 6308
    Prev
    Next
    INDEX
    Explanations

    mentions of state and federal funding for projects

    oai_token-act-pair · gemini-2.0-flash

    specific terms related to funding and grants

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

    Grants and funding

    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
    contentLoaded
    -0.88
    elemField
    -0.55
     CreateTagHelper
    -0.54
    tanleria
    -0.50
    Bronnen
    -0.48
    ngOnInit
    -0.45
     Ecke
    -0.44
    FunctionFlags
    -0.44
    chenkt
    -0.43
     Roskov
    -0.43
    POSITIVE LOGITS
    FormState
    0.61
     tartalomajánló
    0.61
    ."]
    0.60
    spół
    0.60
     fiscales
    0.58
    ✨:
    0.58
     Competitive
    0.57
     Competitions
    0.57
     Анти
    0.56
    ạo
    0.55
    Activations Density 2.191%

    No Known Activations