© 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. 6630
    Prev
    Next
    INDEX
    Explanations

    the topic of wild horse management

    oai_token-act-pair · gemini-2.0-flash

    farming and land

    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
     farmer
    -0.66
    Alike
    -0.61
    MergeFrom
    -0.61
    nyard
    -0.60
     farm
    -0.59
     agricoles
    -0.58
     farms
    -0.57
     препратки
    -0.57
     agriculture
    -0.56
     farmers
    -0.55
    POSITIVE LOGITS
    ledes
    0.50
    
    0.46
     MARKETING
    0.46
     marketing
    0.46
    essoas
    0.46
    راز
    0.46
    marke
    0.45
    rasco
    0.45
     Haan
    0.45
    IDENTITY
    0.44
    Activations Density 1.312%

    No Known Activations