© 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. 161
    Prev
    Next
    INDEX
    Explanations

    references to years

    oai_token-act-pair · gemini-2.0-flash

    US history

    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
    Pyx
    -0.53
    PostInfinity
    -0.52
    selor
    -0.52
     Kamar
    -0.52
    зулта
    -0.51
    DJANGO
    -0.50
    minecraftforge
    -0.49
     camera
    -0.49
     pymongo
    -0.49
    idazole
    -0.48
    POSITIVE LOGITS
     indisponible
    0.51
    expandindo
    0.50
     Patro
    0.49
     Napole
    0.48
     Nacionales
    0.47
     Magna
    0.46
     thua
    0.46
     dè
    0.45
    арак
    0.44
    HasForeignKey
    0.44
    Activations Density 5.492%

    No Known Activations