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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2474
    Prev
    Next
    INDEX
    Explanations

    disjointed and unrelated content across various topics like religion, personal expression, and identity.

    oai_token-act-pair · gemini-2.0-flash

    religion and spirituality

    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
    GOTREF
    -0.73
     typelib
    -0.69
     Tomo
    -0.60
    ledo
    -0.55
     pinulongan
    -0.55
    RegistryLite
    -0.55
    σσ
    -0.55
    Demografie
    -0.54
    tung
    -0.54
     *>(
    -0.53
    POSITIVE LOGITS
     IndexError
    0.61
     vectorielle
    0.57
    abancı
    0.57
     ThemeData
    0.57
    XmlAccessorType
    0.55
     समीक्षक
    0.55
     TAMBIÉN
    0.53
    räger
    0.52
     onBind
    0.52
    Parcelize
    0.51
    Activations Density 1.424%

    No Known Activations