© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4053
    Prev
    Next
    INDEX
    Explanations

    words related to baseball scores and statistics

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pitching
    -0.86
     bat
    -0.84
     Major
    -0.82
    Major
    -0.82
    Pitch
    -0.78
     catcher
    -0.77
     Pitch
    -0.77
     pitched
    -0.74
    pitch
    -0.72
    major
    -0.71
    POSITIVE LOGITS
    Personensuche
    0.74
    EndContext
    0.68
     nahilalakip
    0.68
    oa̍t
    0.68
    principalColumn
    0.65
    verwijspagina
    0.64
    الدراسه
    0.63
    JspWriter
    0.63
    الحياه
    0.62
    AccessorTable
    0.62
    Activations Density 0.661%

    No Known Activations