© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14499
    Prev
    Next
    INDEX
    Explanations

    sentences related to baseball statistics and lists of players

    oai_token-act-pair · gemini-2.0-flash

    programming language tokens or terms

    np_token-act-pair-logits · gpt-4o-mini

    baseball

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    webElementXpaths
    -0.75
     Administrativna
    -0.62
    rungsseite
    -0.60
     BioLib
    -0.54
    Jeografia
    -0.52
     Regierung
    -0.49
     ddelweddau
    -0.48
     Suivez
    -0.48
     Autres
    -0.48
    iertamente
    -0.46
    POSITIVE LOGITS
     snippetHide
    0.69
     مشين
    0.66
     >=",
    0.65
    RegistryLite
    0.63
     Pam
    0.63
    addPreferredGap
    0.59
    Demografia
    0.54
     useAppContext
    0.54
     Ex
    0.54
     تكبرها
    0.54
    Activations Density 0.815%

    No Known Activations