© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    code snippets with nested conditional statements and react components

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
     autorytatywna
    -0.61
     coel
    -0.56
    发表于
    -0.56
    ReusableCell
    -0.53
     xrange
    -0.53
    Portail
    -0.52
    MeasureSpec
    -0.52
    AndEndTag
    -0.52
     Италијани
    -0.52
    EClass
    -0.52
    POSITIVE LOGITS
    ChildScrollView
    0.58
     الحره
    0.52
    ГЛА
    0.49
    ref
    0.49
    numerusform
    0.49
    TagMode
    0.47
     ref
    0.47
     abgerufen
    0.47
    "}";
    0.47
    #
    0.47
    Activations Density 0.458%

    No Known Activations