© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7551
    Prev
    Next
    INDEX
    Explanations

    phrases involving the combination of "how" and "to".

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     snippetHide
    -0.97
    Hentet
    -0.82
     وتسجيلات
    -0.73
    principalColumn
    -0.70
    saraba
    -0.68
    Personensuche
    -0.67
     Meksiku
    -0.65
    новниш
    -0.65
    ineno
    -0.63
    aptation
    -0.62
    POSITIVE LOGITS
     approach
    0.54
     hånd
    0.52
     remedy
    0.52
     façons
    0.50
     circumvent
    0.45
     efficiently
    0.44
     properly
    0.43
     method
    0.43
     Approach
    0.43
     solucion
    0.43
    Activations Density 1.262%

    No Known Activations