© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10738
    Prev
    Next
    INDEX
    Explanations

    the prefix "pro" or "anti" related to political or legal content.

    oai_token-act-pair · gemini-2.0-flash

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -2.28
    '
    -0.73
    DockStyle
    -0.67
    ’
    -0.64
     disambiguazione
    -0.56
    NameInMap
    -0.55
    "
    -0.53
     للمعارف
    -0.52
    //
    -0.52
     is
    -0.52
    POSITIVE LOGITS
     continents
    0.73
     MaterialApp
    0.68
     labours
    0.65
    ütün
    0.63
     normaux
    0.62
     exponentially
    0.62
    SequentialGroup
    0.62
     Prose
    0.62
     alrededores
    0.61
     Reasoning
    0.61
    Activations Density 1.038%

    No Known Activations