© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13790
    Prev
    Next
    INDEX
    Explanations

    a variety of discourse markers and sentence fragments

    oai_token-act-pair · gemini-2.0-flash

    hyphenated words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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>
    -0.96
    ja
    -0.44
    it
    -0.41
    u
    -0.41
    pos
    -0.41
    if
    -0.39
    se
    -0.39
     so
    -0.39
    raz
    -0.38
    tu
    -0.38
    POSITIVE LOGITS
     Efq
    0.87
     Theſe
    0.83
     Monfieur
    0.78
     فريبيس
    0.77
    AutoresizingMask
    0.74
     myſelf
    0.73
     Majefty
    0.71
     reaſon
    0.70
     ſeveral
    0.68
    ^(@)
    0.68
    Activations Density 0.189%

    No Known Activations