© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    snippets of python code related to plotting with colors

    oai_token-act-pair · gemini-2.0-flash

    code and plots

    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
     propOrder
    -0.63
    RenderAtEndOf
    -0.61
    saraba
    -0.58
    adaptiveStyles
    -0.56
    jestel
    -0.56
    kuuta
    -0.55
    PositiveButton
    -0.55
    Autoritní
    -0.53
     Audiodateien
    -0.53
     tetrach
    -0.52
    POSITIVE LOGITS
    EndGlobalSection
    0.57
     devoir
    0.52
    RUP
    0.50
    zów
    0.49
     RUM
    0.48
     off
    0.48
     dehors
    0.48
    HttpDelete
    0.47
    لات
    0.46
    Contributed
    0.45
    Activations Density 0.380%

    No Known Activations