© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2161
    Prev
    Next
    INDEX
    Explanations

    references to family history and personal connections to the past.

    oai_token-act-pair · gemini-2.0-flash

    family history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Uncle
    -1.47
    Uncle
    -1.45
     uncle
    -1.45
     Aunt
    -1.41
     aunt
    -1.38
    Aunt
    -1.32
     uncles
    -1.23
     Dad
    -1.23
     dad
    -1.19
    Dad
    -1.19
    POSITIVE LOGITS
     CreateTagHelper
    0.64
    setzt
    0.58
    setViewName
    0.54
    UnsafeEnabled
    0.46
    gio
    0.46
     grand
    0.45
     Salomon
    0.45
    atiles
    0.44
    Peny
    0.44
    folie
    0.44
    Activations Density 2.495%

    No Known Activations