© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16255
    Prev
    Next
    INDEX
    Explanations

    the word "share" or "limit" or forms of the word "end"

    oai_token-act-pair · gemini-2.0-flash

    allocation or spreading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     "'");
    -0.72
    出版年
    -0.71
    ()]
    -0.69
     gewiß
    -0.69
     [],
    -0.67
    Климат
    -0.66
     AssemblyCompany
    -0.66
     }}"></
    -0.66
     freilich
    -0.65
    ()")
    -0.64
    POSITIVE LOGITS
    abstractmethod
    0.61
     collaborate
    0.59
    sitivity
    0.58
    ModelSerializer
    0.58
    ёх
    0.58
     contaminate
    0.57
     notify
    0.57
    estias
    0.56
    CURLOPT
    0.55
     confuse
    0.55
    Activations Density 0.389%

    No Known Activations