© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2631
    Prev
    Next
    INDEX
    Explanations

    instances of separation or division.

    oai_token-act-pair · gemini-2.0-flash

    Split

    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
    subpackage
    -0.44
    dis
    -0.43
    httphttps
    -0.42
     Vek
    -0.40
    atica
    -0.39
    thin
    -0.39
     Cáceres
    -0.39
    キス
    -0.39
     forgive
    -0.38
     presented
    -0.38
    POSITIVE LOGITS
    ChildScrollView
    0.91
     createState
    0.82
    contentLoaded
    0.80
    IntoConstraints
    0.79
     ContentValues
    0.77
    LLocation
    0.72
    enterOuterAlt
    0.72
     الاطلاع
    0.66
    SharedCtor
    0.66
     onBind
    0.65
    Activations Density 6.985%

    No Known Activations