© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 99
    Prev
    Next
    INDEX
    Explanations

    academic discussions of electrical engineering, particularly regarding sources and modeling

    oai_token-act-pair · gemini-2.0-flash

    accuracy indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    wieś
    -0.66
     مشين
    -0.66
     typelib
    -0.59
    IVEREF
    -0.57
     kaarangay
    -0.57
     procedere
    -0.55
     resourceCulture
    -0.53
     исто
    -0.53
    झे
    -0.53
     Strick
    -0.52
    POSITIVE LOGITS
    #+#
    0.73
    :+:
    0.60
    PMailer
    0.57
    awaiter
    0.54
    ::_('
    0.52
    MOQ
    0.49
    addGap
    0.48
    ]")]
    0.47
     useRouter
    0.47
    munk
    0.46
    Activations Density 2.699%

    No Known Activations