© 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. 8610
    Prev
    Next
    INDEX
    Explanations

    instances of people discussing a topic

    oai_token-act-pair · gemini-2.0-flash

    words related to calling or communication

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

    call

    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
    ंदीखरीदारी
    -0.74
    AsUp
    -0.73
    PyExc
    -0.72
    Obrázky
    -0.69
     виправивши
    -0.68
     pinulongan
    -0.65
    WebElementEntity
    -0.65
     propOrder
    -0.64
    mybatisplus
    -0.64
     Roskov
    -0.62
    POSITIVE LOGITS
     call
    3.75
     calls
    3.30
    call
    3.27
     Call
    3.23
    Call
    3.17
     CALL
    3.05
     calling
    2.98
     Calls
    2.89
    CALL
    2.78
    calls
    2.78
    Activations Density 6.140%

    No Known Activations