© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14106
    Prev
    Next
    INDEX
    Explanations

    phrases that mention limitations

    oai_token-act-pair · gemini-2.0-flash

    comparisons and contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ware
    -0.45
     району
    -0.44
    χος
    -0.43
    IntPtr
    -0.43
    Max
    -0.42
     Maximum
    -0.42
    Lim
    -0.41
    MainActivity
    -0.41
    max
    -0.40
    gars
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    1.33
    InjectAttribute
    1.01
    findpost
    0.95
    InstrumentedTest
    0.95
    ValueGeneration
    0.94
    AddTagHelper
    0.93
    IsContent
    0.92
    awtextra
    0.91
    SequentialGroup
    0.90
    
    0.89
    Activations Density 1.348%

    No Known Activations