© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13595
    Prev
    Next
    INDEX
    Explanations

    phrases that express evaluation or importance.

    oai_token-act-pair · gemini-2.0-flash

    red

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    verwijspagina
    -0.59
    contentLoaded
    -0.57
    TargetException
    -0.52
     @"/
    -0.50
    тература
    -0.49
     DataTypes
    -0.48
    JsonHelper
    -0.48
    DataColumn
    -0.47
     eint
    -0.47
     noDo
    -0.46
    POSITIVE LOGITS
     red
    1.57
     deal
    1.23
    red
    1.22
     Red
    1.11
    Red
    1.08
     Deal
    1.03
     RED
    1.03
    RED
    1.00
     DEAL
    0.97
    Deal
    0.94
    Activations Density 2.119%

    No Known Activations