© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12245
    Prev
    Next
    INDEX
    Explanations

    what appears to be proper nouns, including acronyms, abbreviations, and brand names

    oai_token-act-pair · gemini-2.0-flash

    CFC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _));
    -0.95
    "]);
    -0.84
    ]),
    -0.75
    енча
    -0.75
    */].
    -0.74
     Jefus
    -0.74
    ()]
    -0.73
    PreferredItem
    -0.73
     myſelf
    -0.72
     ſtate
    -0.71
    POSITIVE LOGITS
     CreateTagHelper
    0.63
    хіво
    0.43
     cast
    0.38
    شك
    0.38
    cast
    0.37
    atzen
    0.36
    withId
    0.36
    ULATIONS
    0.35
     cong
    0.35
    Sklici
    0.35
    Activations Density 5.427%

    No Known Activations