© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15067
    Prev
    Next
    INDEX
    Explanations

    initials followed by a period, and sometimes the word "al"

    oai_token-act-pair · gemini-2.0-flash

    Citations and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ,
    -0.88
    â
    -0.47
    шт
    -0.44
    setopt
    -0.42
    StoreMessageInfo
    -0.40
     serez
    -0.40
    Clik
    -0.40
    OwnProperty
    -0.39
    texttt
    -0.39
    putExtra
    -0.39
    POSITIVE LOGITS
    ,"
    0.79
    ."),
    0.74
    />,
    0.70
     />,
    0.69
     useRouter
    0.66
    .
    0.64
    ),
    0.63
    ,'"
    0.61
    îtra
    0.61
    //}
    0.59
    Activations Density 1.315%

    No Known Activations