© 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. 9498
    Prev
    Next
    INDEX
    Explanations

    HTML markup and phone numbers

    oai_token-act-pair · gemini-2.0-flash

    HTML/website-related

    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
     purpoſe
    -0.69
     Efq
    -0.68
     myſelf
    -0.65
     uſe
    -0.64
     uſ
    -0.63
     firſt
    -0.63
     itſelf
    -0.63
     Monfieur
    -0.61
     fhew
    -0.61
     laſt
    -0.60
    POSITIVE LOGITS
    kloped
    0.72
    argout
    0.55
     MenuView
    0.55
    homonymie
    0.54
    MemoryWarning
    0.52
    1
    0.52
    Geplaatst
    0.51
    -
    0.49
    MigrationBuilder
    0.48
    :+:
    0.48
    Activations Density 7.432%

    No Known Activations