© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    conditional statements ("if...then"), often related to making decisions or considering possibilities.

    oai_token-act-pair · gemini-2.0-flash

    she

    np_max-act-logits · gemini-2.0-flash
    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
     her
    -0.92
    Her
    -0.84
     Her
    -0.79
    her
    -0.68
     hers
    -0.66
     HER
    -0.62
     him
    -0.56
    herz
    -0.54
     RIPRODUZIONE
    -0.50
     herre
    -0.49
    POSITIVE LOGITS
     she
    1.02
     sie
    1.00
     sh
    0.90
     SHE
    0.88
    she
    0.85
    SHE
    0.84
     sho
    0.83
     shell
    0.78
    UnknownFieldSet
    0.77
     propOrder
    0.75
    Activations Density 1.643%

    No Known Activations