© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14844
    Prev
    Next
    INDEX
    Explanations

    phrases found in legal documents, software licenses, or code

    oai_token-act-pair · gemini-2.0-flash

    any

    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
     BOTH
    -2.05
     ANYTHING
    -2.00
     EVERYONE
    -1.97
     ANYONE
    -1.97
     EACH
    -1.96
     EVERYTHING
    -1.95
     NOTHING
    -1.94
     EXACTLY
    -1.91
     Monfieur
    -1.90
     EVERY
    -1.89
    POSITIVE LOGITS
    <eos>
    1.17
     
    1.13
     The
    1.11
     N
    1.02
     P
    0.98
     S
    0.98
     No
    0.97
     A
    0.97
     the
    0.96
     L
    0.94
    Activations Density 3.644%

    No Known Activations