© 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. 8481
    Prev
    Next
    INDEX
    Explanations

    mentions of baseball games, including players, positions, and game events

    oai_token-act-pair · gemini-2.0-flash

    terms related to strikes in baseball

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

    baseball "strike"

    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
    Билгалдахарш
    -0.56
    ]^{-
    -0.52
    rungsseite
    -0.52
    monte
    -0.50
     Donc
    -0.50
     Tanah
    -0.49
    WRP
    -0.49
    ifon
    -0.48
    ագրություններ
    -0.48
    につなが
    -0.48
    POSITIVE LOGITS
    出版年
    0.75
     strike
    0.67
    strike
    0.60
    out
    0.58
    PreferredItem
    0.55
    EDEFAULT
    0.53
     strikes
    0.52
     Strike
    0.51
    TemporalType
    0.51
     out
    0.51
    Activations Density 0.745%

    No Known Activations