© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14669
    Prev
    Next
    INDEX
    Explanations

    descriptions of solid body electric guitars

    oai_token-act-pair · gemini-2.0-flash

    guitars and instruments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     giù
    -0.58
     tabs
    -0.54
     reed
    -0.53
    Slap
    -0.52
     tabl
    -0.50
     Tabs
    -0.48
    quias
    -0.48
     numériques
    -0.47
     pluck
    -0.47
     cepat
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.60
     short
    0.59
    Obrázky
    0.57
    mapStateToProps
    0.56
    Activité
    0.55
     &___
    0.52
    sidemargin
    0.52
    JspWriter
    0.52
    Short
    0.51
    rceil
    0.51
    Activations Density 0.552%

    No Known Activations