© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    words commonly appearing in posts on web forums

    oai_token-act-pair · gemini-2.0-flash

    explanation

    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
    WebElementEntity
    -0.73
     فريبيس
    -0.65
    出版年
    -0.58
    ⓧ
    -0.57
    LookAnd
    -0.55
    principalColumn
    -0.54
     invokingState
    -0.54
    featureID
    -0.54
    OfWork
    -0.52
     AssemblyCompany
    -0.52
    POSITIVE LOGITS
     berarti
    0.55
    MemoryWarning
    0.51
    TypedDataSet
    0.50
    AxisAlignment
    0.50
    PhysRevLett
    0.50
     signifies
    0.49
    ThemeOverlay
    0.49
     anlam
    0.48
    いった
    0.47
    Solid
    0.47
    Activations Density 1.178%

    No Known Activations