© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8782
    Prev
    Next
    INDEX
    Explanations

    words in Indian names and Indian movie names

    oai_token-act-pair · gemini-2.0-flash

    various text snippets

    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
    SharedDtor
    -0.69
     WPS
    -0.64
     OSP
    -0.62
    protoimpl
    -0.61
    InjectAttribute
    -0.60
     subterranean
    -0.59
     autorytatywna
    -0.58
     Catholicism
    -0.58
     виправивши
    -0.57
     DVB
    -0.57
    POSITIVE LOGITS
     jij
    0.50
     sahaja
    0.47
     élas
    0.46
     ganda
    0.44
     তারিখ
    0.44
     tarik
    0.43
     dommages
    0.43
    TintMode
    0.43
     makl
    0.42
     /\.(
    0.42
    Activations Density 3.902%

    No Known Activations