© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7619
    Prev
    Next
    INDEX
    Explanations

    text describing car problems

    oai_token-act-pair · gemini-2.0-flash

    gears problems

    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
    NameInMap
    -0.75
    الحياه
    -0.73
    GeoNames
    -0.67
    InitVars
    -0.67
    EndTag
    -0.67
    AntiForgeryToken
    -0.65
    QMetaType
    -0.65
    tonode
    -0.64
     <=",
    -0.63
    IContainer
    -0.62
    POSITIVE LOGITS
     Bucure
    0.54
    gelt
    0.51
    ული
    0.50
    ברס
    0.50
    ilanth
    0.47
     rapt
    0.46
    Salta
    0.46
    ക്ക്
    0.45
     sanguí
    0.45
     pears
    0.45
    Activations Density 3.379%

    No Known Activations