© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    the verb 'play' within a sentence

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "play"

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

    play

    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
    MigrationBuilder
    -0.93
     propOrder
    -0.89
     للمعارف
    -0.85
    CppCodeGen
    -0.85
    发表于
    -0.84
    parsedMessage
    -0.82
    TintMode
    -0.82
    mybatisplus
    -0.79
     estimés
    -0.79
    Personendaten
    -0.78
    POSITIVE LOGITS
     a
    0.69
     an
    0.62
    kowania
    0.48
     different
    0.47
    otter
    0.47
     only
    0.46
     robust
    0.46
    orgs
    0.46
    ovas
    0.44
     well
    0.43
    Activations Density 0.561%

    No Known Activations