© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13941
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are used in academic papers or law references

    oai_token-act-pair · gemini-2.0-flash

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vœux
    -0.90
     attentes
    -0.90
     
    -0.90
     pouvoirs
    -0.89
     blessés
    -0.86
     inconvénients
    -0.84
     esetben
    -0.83
    scenarios
    -0.83
     nuages
    -0.82
    sensors
    -0.80
    POSITIVE LOGITS
     ―――――
    1.20
     ſche
    1.17
     iſt
    1.13
     Reſ
    1.10
     Diſ
    1.10
     Eſ
    1.07
     lenker
    1.06
     Perſ
    1.03
    OGND
    1.02
     Conſ
    0.99
    Activations Density 4.629%

    No Known Activations