© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    passages discussing marketing, consumers, and data trends

    oai_token-act-pair · gemini-2.0-flash

    markets and user behavior

    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
     iprot
    -0.82
    HomeAsUpEnabled
    -0.75
     resourceCulture
    -0.73
    UrlResolution
    -0.71
     pinulongan
    -0.70
     CreateTagHelper
    -0.66
    PhysRevD
    -0.66
    endpush
    -0.65
    PhysRevLett
    -0.64
     OFDb
    -0.63
    POSITIVE LOGITS
    AxisAlignment
    0.47
     Glaser
    0.46
    executable
    0.43
    URED
    0.43
     pegat
    0.43
    urer
    0.42
     skew
    0.41
    FACT
    0.41
    ured
    0.41
    InSection
    0.41
    Activations Density 10.675%

    No Known Activations