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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8617
    Prev
    Next
    INDEX
    Explanations

    words pertaining to people playing a competitive sport and/or commentary on their probable future in the sport

    oai_token-act-pair · gemini-2.0-flash

    Sports articles

    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
    ImageContext
    -0.68
     FetchType
    -0.56
    getDescriptor
    -0.55
    XmlAccessType
    -0.54
    Jîn
    -0.53
    DockStyle
    -0.53
    <bos>
    -0.51
    клопе
    -0.51
     daze
    -0.50
    ChildScrollView
    -0.50
    POSITIVE LOGITS
     surla
    0.63
    +#+#
    0.56
    ContentAsync
    0.56
     Autorizaciones
    0.55
     nahilalakip
    0.55
     lenker
    0.53
    arithmic
    0.51
    PUBLISHED
    0.50
    مصادر
    0.49
     Cataloging
    0.49
    Activations Density 2.268%

    No Known Activations