© 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. 7962
    Prev
    Next
    INDEX
    Explanations

    low-level code, architecture descriptions, and hardware configurations

    oai_token-act-pair · gemini-2.0-flash

    ="

    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
    Hentet
    -0.72
    argout
    -0.71
    principalTable
    -0.69
     Chwiliwch
    -0.68
    ScopeManager
    -0.68
    featureID
    -0.66
    Nationalité
    -0.66
    SourceChecksum
    -0.65
    CppCodeGen
    -0.65
     FormData
    -0.62
    POSITIVE LOGITS
     Inſ
    0.49
     Reſ
    0.49
     Chriftian
    0.48
     purpoſe
    0.47
     Diſ
    0.47
     Majefty
    0.46
     Theſe
    0.46
     مرئيه
    0.45
     Perſ
    0.43
     againſt
    0.43
    Activations Density 11.101%

    No Known Activations