© 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. 2847
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotion, thanks, and connection between people

    oai_token-act-pair · gemini-2.0-flash

    intensifiers like "very"

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

    very

    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
    Vidite
    -0.45
     Вікіпе
    -0.44
    RTEX
    -0.43
    Demografie
    -0.42
    Fast
    -0.41
    Soon
    -0.41
    Quick
    -0.41
     préférence
    -0.41
    RefNanny
    -0.41
    //-->
    -0.40
    POSITIVE LOGITS
     very
    1.78
    very
    1.49
    Very
    1.45
     VERY
    1.43
     muito
    1.40
    VERY
    1.34
     Very
    1.33
     molto
    1.28
     immensely
    1.26
     sehr
    1.22
    Activations Density 1.641%

    No Known Activations