© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13898
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words and phrases, especially those relating to military units and place names

    oai_token-act-pair · gemini-2.0-flash

    Lithuanian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     незавершена
    -0.79
    onViewCreated
    -0.77
    RenderAtEndOf
    -0.71
    DATABASES
    -0.70
     ddelweddau
    -0.68
     propOrder
    -0.67
     ujednoznacz
    -0.67
    AndEndTag
    -0.65
    ActionCreators
    -0.64
    BeginContext
    -0.63
    POSITIVE LOGITS
    dyti
    0.62
    tų
    0.46
    vų
    0.46
    ianum
    0.45
    IANA
    0.45
    ISCH
    0.44
     diamètre
    0.44
    mą
    0.43
    žius
    0.43
    tą
    0.43
    Activations Density 0.718%

    No Known Activations