© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 265
    Prev
    Next
    INDEX
    Explanations

    intensifiers and words used for emphasis such as "very", "really", and words written in all capital letters

    oai_token-act-pair · gemini-2.0-flash

    Negative experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DockStyle
    -0.60
    complexContent
    -0.60
    roek
    -0.59
    )))));
    -0.56
    audiovisuel
    -0.56
    ajuato
    -0.55
    hires
    -0.52
     Nema
    -0.52
    ieszka
    -0.52
    crimin
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.66
     moglie
    0.54
     doccia
    0.53
    DropTable
    0.51
     generazione
    0.50
     contenir
    0.49
    Население
    0.49
     tendenza
    0.48
     دیکھیے
    0.48
     découver
    0.47
    Activations Density 2.747%

    No Known Activations