© 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. 15314
    Prev
    Next
    INDEX
    Explanations

    words that express personal opinions, judgements, or feelings, as well as a few words related to time

    oai_token-act-pair · gemini-2.0-flash

    indicating "these"

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

    these

    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
    TagMode
    -0.77
    ngdoc
    -0.73
     مرئيه
    -0.66
    enderror
    -0.61
    andExpect
    -0.57
    RegressionTest
    -0.56
    lgari
    -0.56
     تانيه
    -0.54
    zuli
    -0.54
    Geplaatst
    -0.53
    POSITIVE LOGITS
     these
    3.42
    these
    2.91
    These
    2.72
     These
    2.70
     THESE
    2.39
     estos
    2.19
    这些
    2.14
    這些
    2.11
    これらの
    2.09
     этих
    2.06
    Activations Density 3.496%

    No Known Activations