© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13873
    Prev
    Next
    INDEX
    Explanations

    Russian related to offers and requests

    oai_token-act-pair · gemini-2.0-flash

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     produktów
    -0.41
     stili
    -0.40
     lose
    -0.40
     lost
    -0.40
     ervan
    -0.40
     perdita
    -0.40
    いが
    -0.40
     Loose
    -0.39
     loose
    -0.39
     любви
    -0.39
    POSITIVE LOGITS
     doInBackground
    0.79
    تقاوى
    0.79
     CreateTagHelper
    0.78
    ंदीखरीदारी
    0.75
    extAlignment
    0.73
    URLException
    0.71
     kaarangay
    0.68
    esModule
    0.68
    BufferException
    0.67
     OFDb
    0.66
    Activations Density 0.351%

    No Known Activations