© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12928
    Prev
    Next
    INDEX
    Explanations

    words relating to cause and effect / stimulus and response

    oai_token-act-pair · gemini-2.0-flash

    estimate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     stop
    -0.44
    IBAction
    -0.42
    mony
    -0.40
     option
    -0.39
    smile
    -0.39
    ACY
    -0.38
    spyOn
    -0.38
     ф
    -0.38
     on
    -0.38
    ី
    -0.38
    POSITIVE LOGITS
     kasarigan
    0.86
    出版年
    0.85
    TagMode
    0.85
    GraphicsUnit
    0.80
     AssemblyVersion
    0.78
    EDEFAULT
    0.77
     архивлан
    0.77
    verwijspagina
    0.77
    InvalidProtocol
    0.76
     BoxFit
    0.75
    Activations Density 5.743%

    No Known Activations