© 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. 16358
    Prev
    Next
    INDEX
    Explanations

    articles related to legal situations and geopolitical events in countries in Africa

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    FormTagHelper
    -0.67
     autorytatywna
    -0.64
    SharedDtor
    -0.62
    AdapterView
    -0.54
    fromnode
    -0.54
     Савезне
    -0.54
    новништво
    -0.53
     packageName
    -0.52
    Einzelnachweise
    -0.52
    GOTREF
    -0.52
    POSITIVE LOGITS
     lèvres
    0.56
     réfugiés
    0.55
     fumée
    0.51
     émissions
    0.51
     missione
    0.49
     candidats
    0.49
     juges
    0.49
    ukų
    0.48
     touristes
    0.48
     vérit
    0.48
    Activations Density 3.375%

    No Known Activations