© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4987
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "middle," often in the context of age, location, or compromise

    oai_token-act-pair · gemini-2.0-flash

    Middle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ChildIndex
    -0.55
    perator
    -0.54
    corpion
    -0.53
    arcoma
    -0.52
    Dated
    -0.48
    CELLANEOUS
    -0.48
    nhold
    -0.47
     Courant
    -0.47
    getAttributes
    -0.46
     Half
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.94
    webElementXpaths
    0.74
    InstanceState
    0.69
     للاسماء
    0.65
    awtextra
    0.65
     الاطلاع
    0.62
     ground
    0.60
    addGap
    0.58
    BeginContext
    0.55
    imageshack
    0.55
    Activations Density 0.923%

    No Known Activations