© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16080
    Prev
    Next
    INDEX
    Explanations

    the word 'whose' and other words that are near it in the text, and are somewhat related to describing things

    oai_token-act-pair · gemini-2.0-flash

    whose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    stånd
    -0.57
     slutet
    -0.56
     mús
    -0.56
     hvert
    -0.55
     berätt
    -0.54
     Anche
    -0.53
     forcible
    -0.53
    \
    -0.52
     batalha
    -0.52
    ial
    -0.52
    POSITIVE LOGITS
    EDEFAULT
    0.97
    elemField
    0.93
    <bos>
    0.74
    Portály
    0.72
    GraphicsUnit
    0.71
    ”]
    0.71
    GEBURTSDATUM
    0.71
    WriteTagHelper
    0.70
    WithIOException
    0.70
    ContentAlignment
    0.70
    Activations Density 3.129%

    No Known Activations