© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12146
    Prev
    Next
    INDEX
    Explanations

    mentions of production of olive oil

    oai_token-act-pair · gemini-2.0-flash

    picking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     فريبيس
    -0.80
     Jesuits
    -0.61
    Latch
    -0.58
    ITest
    -0.56
    Obrázky
    -0.55
     sympy
    -0.52
     epig
    -0.51
    bjs
    -0.50
     Azam
    -0.49
     iprot
    -0.49
    POSITIVE LOGITS
     picking
    0.72
     pick
    0.68
     Pick
    0.66
    Pick
    0.64
     picks
    0.63
    pick
    0.63
     PICK
    0.61
     picked
    0.60
    picking
    0.60
    Picking
    0.58
    Activations Density 3.116%

    No Known Activations