© 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. 9385
    Prev
    Next
    INDEX
    Explanations

    a pair of numbers, often years, separated by a hyphen or en-dash

    oai_token-act-pair · gemini-2.0-flash

    technical writing/data

    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
    3
    -0.94
     three
    -0.84
    ３
    -0.74
     Three
    -0.74
    three
    -0.73
    THREE
    -0.72
     ketiga
    -0.71
    三
    -0.70
     THREE
    -0.69
    Three
    -0.68
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     intptr
    0.58
    tableFuture
    0.55
     protoimpl
    0.53
    yarnpkg
    0.51
    rungsseite
    0.50
    είου
    0.50
    Nuorodos
    0.49
    protoimpl
    0.49
    slidesPer
    0.49
    Activations Density 9.047%

    No Known Activations