© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13856
    Prev
    Next
    INDEX
    Explanations

    the word 'the' with varying amounts of context

    oai_token-act-pair · gemini-2.0-flash

    say rooms

    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
     living
    -0.77
     Living
    -0.76
    Living
    -0.71
    living
    -0.71
     LIVING
    -0.70
    tvguidetime
    -0.66
    LIVING
    -0.66
    +#+#
    -0.62
    ">//
    -0.56
    !*\
    -0.54
    POSITIVE LOGITS
     BoxDecoration
    0.59
    delwed
    0.52
    amoan
    0.51
     BorderSide
    0.50
    WebControls
    0.50
     cooldown
    0.49
     wyn
    0.49
    getCause
    0.48
    WireFormat
    0.47
    barco
    0.47
    Activations Density 2.853%

    No Known Activations