© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    phrases discussing rankings and ratings

    oai_token-act-pair · gemini-2.0-flash

    leading position

    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
    setVerticalGroup
    -0.83
     الدولى
    -0.60
     Existing
    -0.54
    botto
    -0.52
    Existing
    -0.52
     eingel
    -0.52
    ablecer
    -0.52
     empre
    -0.51
    ⓘ
    -0.50
    NUMX
    -0.50
    POSITIVE LOGITS
     ahead
    1.42
    ahead
    1.19
     Ahead
    1.09
     AHEAD
    1.08
    Ahead
    1.03
     beating
    0.96
     beat
    0.96
     devant
    0.90
     beaten
    0.89
     davanti
    0.82
    Activations Density 1.138%

    No Known Activations