© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11058
    Prev
    Next
    INDEX
    Explanations

    the last name "Bas" and similar short names possibly related to churches

    oai_token-act-pair · gemini-2.0-flash

    Bas

    np_max-act-logits · gemini-2.0-flash

    Bas

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     es
    -0.43
     a
    -0.38
    RES
    -0.38
    ES
    -0.38
     (
    -0.37
    AT
    -0.37
      
    -0.36
     cost
    -0.36
     द
    -0.36
     
    -0.36
    POSITIVE LOGITS
    bootstrapcdn
    1.03
     defaultstate
    1.02
     AssemblyProduct
    1.00
     ddelweddau
    0.93
    脚注の使い方
    0.93
     ویکی‌پدیای
    0.90
    BufferException
    0.88
    SourceChecksum
    0.87
    ISupport
    0.85
     estekak
    0.85
    Activations Density 1.349%

    No Known Activations