© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    technical descriptions that give options

    oai_token-act-pair · gemini-2.0-flash

    diverse text snippets

    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
     &_
    -0.66
    DebuggerNonUser
    -0.62
    SequentialGroup
    -0.60
    utilisons
    -0.60
    ItemBackground
    -0.59
    NewUrlParser
    -0.57
    hdashline
    -0.57
    (&_
    -0.57
    PIL
    -0.56
    VersionUID
    -0.55
    POSITIVE LOGITS
    getRuntime
    0.46
    RenderAtEndOf
    0.43
     CharSequence
    0.43
    ⌘
    0.42
    pyx
    0.42
    äki
    0.41
     continuant
    0.40
    Customers
    0.40
    acyjna
    0.40
    play
    0.38
    Activations Density 4.580%

    No Known Activations