© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    words commonly found in music reviews and biographies.

    oai_token-act-pair · gemini-2.0-flash

    words related to music and performance

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

    radio programming

    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
    +#+#
    -0.79
    tableFuture
    -0.70
    ViewImports
    -0.66
     متعلقه
    -0.61
    RepeatedField
    -0.57
    parsedMessage
    -0.56
    FunctionFlags
    -0.55
    ؤلاء
    -0.54
     transfieras
    -0.54
    icism
    -0.53
    POSITIVE LOGITS
     programmers
    0.65
     spins
    0.58
     programmation
    0.57
     Spins
    0.56
     spinning
    0.56
     Spin
    0.54
     booking
    0.53
     Zane
    0.53
     air
    0.52
     rock
    0.52
    Activations Density 1.130%

    No Known Activations