© 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. 14663
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to baseball festivities at the Reds Hall of Fame

    oai_token-act-pair · gemini-2.0-flash

    words related to membership and seasons

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

    Season, Membership

    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
    UserScript
    -0.82
    haikusbot
    -0.73
    تقاوى
    -0.72
     الرياضيه
    -0.68
    CppMethod
    -0.68
    RetentionPolicy
    -0.66
    BASELINE
    -0.66
    DBNull
    -0.62
     bookId
    -0.62
    fony
    -0.62
    POSITIVE LOGITS
     season
    0.69
    Season
    0.65
     Season
    0.65
     Members
    0.62
     corporate
    0.60
    season
    0.58
     members
    0.57
    elstein
    0.57
     Corporate
    0.54
    Membership
    0.54
    Activations Density 1.044%

    No Known Activations