© 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. 791
    Prev
    Next
    INDEX
    Explanations

    seemingly random words or parts of words or dates and Italian words, sometimes near numbers or symbols

    oai_token-act-pair · gemini-2.0-flash

    Code and documentation

    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
     ***!
    -0.59
     betweenstory
    -0.57
     ostavi
    -0.55
    ItemBackground
    -0.55
    UrlResolution
    -0.54
    beelden
    -0.51
     AssemblyTitle
    -0.49
    CopyWith
    -0.48
    nyez
    -0.47
    SerializedName
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.63
     Heeren
    0.55
    rawDesc
    0.55
    Véxase
    0.51
    Джерела
    0.51
    Handlung
    0.51
    gev
    0.51
    варь
    0.50
     MethodInfo
    0.50
    Gemeinden
    0.50
    Activations Density 0.934%

    No Known Activations