© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1192
    Prev
    Next
    INDEX
    Explanations

    words that are part of questions, requests, or directions

    oai_token-act-pair · gemini-2.0-flash

    Forum questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     "..\..\
    -0.65
    GraphicsUnit
    -0.61
     "..\..\..\
    -0.59
    ValueGeneration
    -0.57
     AssemblyVersion
    -0.57
    Билгалдахарш
    -0.53
     OFDb
    -0.51
    UnusedPrivate
    -0.49
    paramref
    -0.47
    شنبه
    -0.46
    POSITIVE LOGITS
    wiek
    0.59
    PerformLayout
    0.57
     betweenstory
    0.54
    unknownFields
    0.53
    IBarButtonItem
    0.52
    crollView
    0.51
    SerializedSize
    0.51
    凰
    0.51
     enlist
    0.51
    ScopeManager
    0.51
    Activations Density 5.134%

    No Known Activations