© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    first person references and positive sentiment about services or products

    oai_token-act-pair · gemini-2.0-flash

    recommendations or positive reviews

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

    positive 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
     '\\;'
    -0.61
     désolés
    -0.55
    NOPQRST
    -0.52
     humeur
    -0.51
    ANTLR
    -0.50
    ISupport
    -0.49
    uxxxx
    -0.49
     مشارکت‌کنندگان
    -0.49
    ](#
    -0.49
     souverain
    -0.48
    POSITIVE LOGITS
     highly
    0.69
    sproz
    0.64
     Highly
    0.60
    writeFieldEnd
    0.57
    highly
    0.57
    Highly
    0.52
    StackNavigator
    0.51
    ItemBackground
    0.49
     recommend
    0.49
    itié
    0.49
    Activations Density 0.933%

    No Known Activations