© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    words related to communication efforts, especially letters and phone calls

    oai_token-act-pair · gemini-2.0-flash

    contacting someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    GEBURTS
    -0.69
    tershire
    -0.63
     invokingState
    -0.61
     verrez
    -0.56
    rachtet
    -0.56
     Bedi
    -0.56
     Schme
    -0.55
    ISupport
    -0.55
     DevComponents
    -0.54
     démocr
    -0.54
    POSITIVE LOGITS
    <bos>
    0.92
     calls
    0.85
     call
    0.84
    Call
    0.79
    call
    0.74
     calling
    0.74
     CALL
    0.73
    calls
    0.68
     Call
    0.68
    CALL
    0.66
    Activations Density 0.721%

    No Known Activations