© 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. 11099
    Prev
    Next
    INDEX
    Explanations

    words ending in "at" plus instances of slang.

    oai_token-act-pair · 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
    polation
    -0.71
    ratulations
    -0.69
    ientôt
    -0.64
    IFORNIA
    -0.63
    RuleContext
    -0.63
    Bronnen
    -0.63
    anical
    -0.62
    bidden
    -0.62
    ualaikum
    -0.61
     bint
    -0.60
    POSITIVE LOGITS
    that
    1.80
     that
    1.78
    That
    1.47
     That
    1.37
    THAT
    1.36
     THAT
    1.30
    thats
    1.02
     bahwa
    1.02
     bahawa
    0.96
     thats
    0.94
    Activations Density 0.200%

    No Known Activations