© 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. 15750
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, places, and organizations, often with associated dates.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    </strong>
    -0.49
    </em>
    -0.43
     $
    -0.43
    <em>
    -0.42
    THAT
    -0.35
     ${
    -0.33
    ⓘ
    -0.32
     nada
    -0.31
    $
    -0.30
    favor
    -0.30
    POSITIVE LOGITS
     الاطلاع
    0.85
     Pelop
    0.74
    клопе
    0.70
     norvég
    0.70
     Bucure
    0.70
     japonais
    0.69
     Kurdish
    0.69
    veien
    0.69
     Jérusalem
    0.69
     lenker
    0.68
    Activations Density 9.830%

    No Known Activations