© 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. 1660
    Prev
    Next
    INDEX
    Explanations

    qualifiers that express degrees of uncertainty

    oai_token-act-pair · gemini-2.0-flash

    uncertain or tentative language

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

    uncertainty words

    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
    Negative Logits
    "}")
    -0.49
    sim
    -0.47
    wts
    -0.46
     whit
    -0.44
    liko
    -0.44
    yship
    -0.44
    "](
    -0.43
    ]][
    -0.43
    :],
    -0.42
    CharStream
    -0.42
    POSITIVE LOGITS
     you
    0.96
     it
    0.85
     these
    0.84
     this
    0.84
     the
    0.82
     they
    0.81
     we
    0.75
     he
    0.74
    ,
    0.69
     today
    0.69
    Activations Density 3.065%

    No Known Activations