© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12624
    Prev
    Next
    INDEX
    Explanations

    the word "name" preceded by "< param"

    oai_token-act-pair · gemini-2.0-flash

    name

    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
     Crash
    -0.55
    vacy
    -0.52
     Voiture
    -0.52
    存于互联网档案馆
    -0.52
    onActivityResult
    -0.52
    <bos>
    -0.51
    yntaxException
    -0.50
     faſt
    -0.49
     ſche
    -0.48
     Nomination
    -0.48
    POSITIVE LOGITS
    הערות
    0.54
    GEBURTSDATUM
    0.53
    TagMode
    0.52
    adaptiveStyles
    0.51
    #+#
    0.50
    ništ
    0.48
     propOrder
    0.47
     CURIAM
    0.46
    šanai
    0.46
     końcu
    0.44
    Activations Density 0.026%

    No Known Activations