© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9749
    Prev
    Next
    INDEX
    Explanations

    words used in food reviews, especially words that can be used to describe how good a restaurant might be

    oai_token-act-pair · gemini-2.0-flash

    specific technical or programming terms

    np_token-act-pair-logits · gpt-4o-mini

    Restaurant reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    /**
    -0.52
    niek
    -0.47
    ctools
    -0.46
     timelapse
    -0.46
     maart
    -0.46
    LabelTagHelper
    -0.45
     NTFS
    -0.44
    tagext
    -0.44
     cromado
    -0.44
     anlaş
    -0.44
    POSITIVE LOGITS
    ="@+
    0.74
    IntoConstraints
    0.67
    WriteAttribute
    0.63
     חיצוניים
    0.62
     препратки
    0.58
     Himo
    0.57
    CodedInputStream
    0.57
    Geplaatst
    0.57
     casual
    0.56
    XmlAccessorType
    0.56
    Activations Density 0.921%

    No Known Activations