© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8247
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters or formatting elements

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MainAxisSize
    -0.59
    ImageContext
    -0.48
    \{\\
    -0.46
    løs
    -0.46
    <bos>
    -0.45
    pakah
    -0.44
    çük
    -0.42
     regionales
    -0.41
     quedado
    -0.41
     puissent
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.84
    principalTable
    0.78
    PerformLayout
    0.72
     Alamy
    0.71
     متعلقه
    0.69
    Geplaatst
    0.68
     للمعارف
    0.67
     Roskov
    0.66
    >*/
    0.66
    SourceChecksum
    0.66
    Activations Density 1.919%

    No Known Activations