© 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. 4970
    Prev
    Next
    INDEX
    Explanations

    the word "pan" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    pan

    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
     (
    -0.99
     I
    -0.93
     a
    -0.88
     N
    -0.86
     S
    -0.84
     of
    -0.84
     R
    -0.80
     E
    -0.78
     A
    -0.77
    <eos>
    -0.77
    POSITIVE LOGITS
     Theſe
    2.08
     itſelf
    2.00
     Efq
    1.98
     Majefty
    1.97
     Monfieur
    1.95
     Jefus
    1.95
     Houſe
    1.91
     houſe
    1.90
     myſelf
    1.88
    ſelf
    1.80
    Activations Density 1.848%

    No Known Activations