© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    words of commonality or usefulness

    oai_token-act-pair · gemini-2.0-flash

    providing examples/lists

    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
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.87
    SourceChecksum
    -0.68
    GraphicsUnit
    -0.61
    Aholisi
    -0.60
     !!!!!
    -0.60
    UnusedPrivate
    -0.60
     !!!!
    -0.59
    photobucket
    -0.57
     sculptured
    -0.55
     समीक्षाएं
    -0.55
    POSITIVE LOGITS
     Notably
    0.68
    Alongside
    0.63
    Czytaj
    0.63
     réjou
    0.62
    ⁠
    0.61
     yalnızca
    0.61
    })*/
    0.59
    tdessen
    0.59
    xically
    0.58
    SupportActionBar
    0.56
    Activations Density 7.238%

    No Known Activations