© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15366
    Prev
    Next
    INDEX
    Explanations

    sports-related match reports mentioning teams, titles, and tournaments.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    rungsseite
    -0.93
     '\\;'
    -0.88
    曖昧さ回避
    -0.66
    awtextra
    -0.60
     متعلقه
    -0.60
    Tikang
    -0.60
    <bos>
    -0.59
    AddTagHelper
    -0.59
    verwijspagina
    -0.58
    RectangleBorder
    -0.58
    POSITIVE LOGITS
    schedulers
    0.50
    ikian
    0.47
     mittleren
    0.46
    ObjectMapper
    0.44
     maioria
    0.44
    mener
    0.43
     compleja
    0.42
    vora
    0.42
    mette
    0.42
    मित
    0.42
    Activations Density 1.228%

    No Known Activations