© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6342
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Facebook and SMS messages in Croatian

    oai_token-act-pair · gemini-2.0-flash

    Foreign language 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_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
     <>",
    -0.72
    NameInMap
    -0.71
    CloseOperation
    -0.66
     Савезне
    -0.64
     <<<<<<<<<<<<<<
    -0.63
    /**
    -0.62
    Datuak
    -0.62
    IntoConstraints
    -0.62
    imread
    -0.61
    stdafx
    -0.59
    POSITIVE LOGITS
    TProtocol
    0.49
    Hulk
    0.46
    しか
    0.45
    Hora
    0.44
     fumar
    0.43
    WTO
    0.42
    readystatechange
    0.41
    ohm
    0.40
     SPEAKER
    0.40
     Sinter
    0.40
    Activations Density 0.376%

    No Known Activations