© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12437
    Prev
    Next
    INDEX
    Explanations

    words related to printing machines, especially the Linotype

    oai_token-act-pair · gemini-2.0-flash

    terms related to musical instruments and keys

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

    Keyboards and organs

    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
     onAnimation
    -0.79
    GEBURTS
    -0.68
     StringTokenizer
    -0.64
     חיצוניים
    -0.63
     دیکھیے
    -0.59
    ніципа
    -0.58
     SafeMath
    -0.57
    astéro
    -0.57
     Administrativna
    -0.57
     crossorigin
    -0.57
    POSITIVE LOGITS
    ódó
    0.59
     organ
    0.58
     org
    0.56
     Organ
    0.55
    WithMany
    0.49
    organ
    0.49
     keyboard
    0.49
    Organ
    0.48
    lccc
    0.47
     command
    0.46
    Activations Density 0.766%

    No Known Activations