© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12045
    Prev
    Next
    INDEX
    Explanations

    the words "bare" and "encounter", with some preference for them appearing near "before" or other prepositions

    oai_token-act-pair · gemini-2.0-flash

    bare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.77
     for
    -0.70
     to
    -0.66
     from
    -0.65
     also
    -0.64
     in
    -0.64
    ,
    -0.64
    ↵
    -0.64
     on
    -0.64
     is
    -0.61
    POSITIVE LOGITS
     ་་
    1.03
     NAL
    0.92
     Hemis
    0.89
     photolibrary
    0.89
    ttemberg
    0.89
     ―――――
    0.89
    ^(@)
    0.85
     BorderSide
    0.83
    dirond
    0.83
    HostException
    0.83
    Activations Density 1.400%

    No Known Activations