© 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. 1871
    Prev
    Next
    INDEX
    Explanations

    words associated with mathematical or computational processes and probability

    oai_token-act-pair · gemini-2.0-flash

    so

    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
     createSprite
    -0.65
     ExecuteAsync
    -0.63
    AnchorStyles
    -0.62
     ivelany
    -0.60
    Clik
    -0.60
     tartalomajánló
    -0.57
    ynen
    -0.57
    ElementException
    -0.57
    glBegin
    -0.57
    providedIn
    -0.56
    POSITIVE LOGITS
     so
    2.38
    so
    1.57
     так
    1.52
     så
    1.43
     כך
    1.37
     So
    1.34
     zodat
    1.33
    So
    1.31
     sehingga
    1.30
     SO
    1.18
    Activations Density 5.028%

    No Known Activations