© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5779
    Prev
    Next
    INDEX
    Explanations

    mentions of required and validated states or properties in what appears to be code

    oai_token-act-pair · gemini-2.0-flash

    required

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Required
    -1.73
    required
    -1.73
     Required
    -1.63
     required
    -1.63
     REQUIRED
    -1.32
    REQUIRED
    -1.25
     requisite
    -0.94
    <bos>
    -0.91
     mandated
    -0.91
     mandatory
    -0.89
    POSITIVE LOGITS
    IntoConstraints
    0.82
    onOptions
    0.54
    OrNil
    0.49
    LayoutInflater
    0.47
    remont
    0.47
    CodeAttribute
    0.47
     BrowserModule
    0.47
     estab
    0.47
    olidated
    0.47
    sights
    0.46
    Activations Density 0.640%

    No Known Activations