© 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. 6449
    Prev
    Next
    INDEX
    Explanations

    words relating to internet network configuration

    oai_token-act-pair · gemini-2.0-flash

    network and wireless technology

    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
     wireless
    -1.36
     Wireless
    -1.25
    Wireless
    -1.23
     Wi
    -1.20
     Wifi
    -1.15
    wireless
    -1.13
     wifi
    -1.13
     WiFi
    -1.10
    Wi
    -1.09
    Wifi
    -1.08
    POSITIVE LOGITS
    rungsseite
    0.68
    Fordítás
    0.59
    SpringBootTest
    0.59
    djangoproject
    0.54
    verwijspagina
    0.53
     BoxFit
    0.52
    GraphicsUnit
    0.51
    EndContext
    0.51
    yakarta
    0.50
    حوالہ
    0.50
    Activations Density 2.720%

    No Known Activations