© 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. 12571
    Prev
    Next
    INDEX
    Explanations

    references to people and the phrase "come hell or high water."

    oai_token-act-pair · gemini-2.0-flash

    person

    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
    ]='\
    -0.66
    ритори
    -0.65
    >--}}
    -0.65
    __;
    -0.65
     pungkas
    -0.65
    ließlich
    -0.62
    \}\\
    -0.61
    Rout
    -0.61
    ilich
    -0.60
     undersigned
    -0.60
    POSITIVE LOGITS
    <bos>
    0.86
    ↵↵
    0.52
    a
    0.51
    .
    0.50
     referenties
    0.50
    etzten
    0.50
    세요
    0.49
    The
    0.49
     aprire
    0.49
     mukana
    0.49
    Activations Density 0.138%

    No Known Activations