© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    references to lessons learned from experience

    oai_token-act-pair · gemini-2.0-flash

    lessons, experiences

    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
    addCriterion
    -0.75
    PerformLayout
    -0.75
     متعلقه
    -0.71
    makeConstraints
    -0.69
     localObject
    -0.62
     AssemblyTitle
    -0.60
    SequentialGroup
    -0.60
     auroit
    -0.59
     ModelExpression
    -0.59
     nargin
    -0.58
    POSITIVE LOGITS
     experience
    0.54
    ellants
    0.49
     Erkennt
    0.48
     esser
    0.45
     O
    0.44
    经验
    0.44
    experience
    0.44
     building
    0.43
     Mal
    0.43
    経験
    0.43
    Activations Density 0.840%

    No Known Activations