© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9682
    Prev
    Next
    INDEX
    Explanations

    phrases containing multiple prepositions and words like "lead to".

    oai_token-act-pair · gemini-2.0-flash

    positive changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Fußballspieler
    -0.49
    IsPostBack
    -0.46
     dobře
    -0.45
     Lordships
    -0.45
     Florentine
    -0.44
     demais
    -0.42
     reemplazar
    -0.42
     térmico
    -0.42
     dupa
    -0.42
    lewati
    -0.41
    POSITIVE LOGITS
     increased
    0.79
     greater
    0.73
    ]--;
    0.73
    WebVitals
    0.73
     significant
    0.72
    govina
    0.71
     fewer
    0.69
     explosions
    0.68
     enhanced
    0.67
     improved
    0.66
    Activations Density 3.845%

    No Known Activations