© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10426
    Prev
    Next
    INDEX
    Explanations

    pronouns and the verb "to be" along with tourist or people

    oai_token-act-pair · gemini-2.0-flash

    tightly packed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ⓧ
    -0.78
     Theſe
    -0.70
    SBATCH
    -0.70
    ItemBackground
    -0.65
     esternos
    -0.63
     Majefty
    -0.63
    SequentialGroup
    -0.60
     ujednoznacz
    -0.58
     whoſe
    -0.58
     referenties
    -0.57
    POSITIVE LOGITS
     squeeze
    1.06
     squeezing
    1.04
     tight
    1.02
     squeezed
    1.01
     packed
    0.99
     crammed
    0.97
    packed
    0.91
     Tight
    0.88
     cramped
    0.88
     tightly
    0.88
    Activations Density 1.288%

    No Known Activations