© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    words ending in "ity", "ly", "rate", " dioxide","ant","izer", "ives", or followed by "out"

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ity
    -0.87
     Monfieur
    -0.69
     Majefty
    -0.68
    StoryboardSegue
    -0.68
    ités
    -0.68
     pleaſure
    -0.67
    ITY
    -0.67
    WriteAttribute
    -0.66
    ities
    -0.65
    itty
    -0.63
    POSITIVE LOGITS
    Autoritní
    0.68
    #+#
    0.64
     lenker
    0.56
    InitStruct
    0.52
    XmlAccessorType
    0.48
    ieR
    0.48
     Ter
    0.46
    └
    0.46
    TRAILING
    0.45
    bollah
    0.44
    Activations Density 9.840%

    No Known Activations