© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5462
    Prev
    Next
    INDEX
    Explanations

    descriptions of the general state of a sports team, like their energy level or emotional state

    oai_token-act-pair · gemini-2.0-flash

    Foreign words and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Velasco
    -0.54
    AnimationsModule
    -0.54
    ⓘ
    -0.50
    lovakia
    -0.49
    iolis
    -0.49
    Prä
    -0.47
    cinogenicity
    -0.47
    VPB
    -0.47
    ypus
    -0.46
     cinnamon
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.88
     nahilalakip
    0.74
    RenderAtEndOf
    0.66
    Referanser
    0.59
    Personensuche
    0.59
    Autoritní
    0.59
     ExecuteAsync
    0.57
    Referencer
    0.57
     الحره
    0.56
    Kilder
    0.55
    Activations Density 1.876%

    No Known Activations