© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1843
    Prev
    Next
    INDEX
    Explanations

    technical academic papers on physics and mathematics

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords

    np_token-act-pair-logits · gpt-4o-mini

    physics theories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     folgender
    -0.53
    bigsqcup
    -0.52
     صوتيه
    -0.52
    Dimethyl
    -0.52
     ExecuteAsync
    -0.51
     Samaria
    -0.51
    zaba
    -0.50
    issement
    -0.49
    erals
    -0.48
    XmlAccessType
    -0.47
    POSITIVE LOGITS
    Clik
    0.62
    NamedQuery
    0.59
     free
    0.57
    free
    0.50
    Osp
    0.49
    InstanceState
    0.48
     pries
    0.48
     plu
    0.47
    flashdata
    0.47
    RegressionTest
    0.47
    Activations Density 2.839%

    No Known Activations