© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15926
    Prev
    Next
    INDEX
    Explanations

    words related to agriculture, especially crops and irrigation

    oai_token-act-pair · gemini-2.0-flash

    olive and citrus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    \{\\
    -0.55
    IBinder
    -0.53
     Cud
    -0.51
     MaterialApp
    -0.50
     kasarigan
    -0.50
     Lad
    -0.49
    apé
    -0.48
    rense
    -0.48
    gwt
    -0.47
    AnchorTagHelper
    -0.46
    POSITIVE LOGITS
     olive
    0.71
     citrus
    0.69
    +:+
    0.65
     lemon
    0.60
    olive
    0.57
    Citrus
    0.57
     يتيمه
    0.57
     orange
    0.57
     olives
    0.56
    niosek
    0.56
    Activations Density 0.942%

    No Known Activations