© 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. 9436
    Prev
    Next
    INDEX
    Explanations

    references to academic papers including at least one of the following terms: (year), et, Robins Rot, and

    oai_token-act-pair · gemini-2.0-flash

    academic papers

    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
    :✨
    -1.10
     AssemblyCulture
    -1.09
     Efq
    -1.04
     Monfieur
    -1.02
    InitVars
    -0.99
    SourceChecksum
    -0.98
     resourceCulture
    -0.93
    HtmlAttribute
    -0.93
     Theſe
    -0.89
    EDEFAULT
    -0.88
    POSITIVE LOGITS
     le
    0.42
     egy
    0.37
     bes
    0.36
    SneakyThrows
    0.36
    ual
    0.35
     Mathis
    0.35
    中的
    0.35
     ter
    0.35
     sj
    0.35
     h
    0.34
    Activations Density 0.549%

    No Known Activations