© 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. 12844
    Prev
    Next
    INDEX
    Explanations

    words having to do with aeronautics and sailing

    oai_token-act-pair · gemini-2.0-flash

    Airplanes and boats

    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
    IsMutable
    -0.79
     beginnetje
    -0.63
    ArgumentParser
    -0.61
    nonatomic
    -0.60
    EndContext
    -0.60
    EndGlobalSection
    -0.59
     TestBed
    -0.59
     AspNetCore
    -0.58
    ChildScrollView
    -0.58
    WriteTagHelper
    -0.57
    POSITIVE LOGITS
     engraçadas
    0.52
    XmlAttribute
    0.51
     dévelo
    0.51
    pasti
    0.51
     précieux
    0.50
     vermelhas
    0.50
     gioielli
    0.49
     Enviar
    0.49
     femininas
    0.48
     vastu
    0.48
    Activations Density 2.202%

    No Known Activations