© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13941
    Prev
    Next
    INDEX
    Explanations

    the word "only" or "and" when preceeded by a modal verb or the word "if", with some sensitivity to phrases related to HTTP requests

    oai_token-act-pair · gemini-2.0-flash

    Hypothetical/Doubt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ModelExpression
    -0.75
    GOTREF
    -0.68
     comuniques
    -0.68
    ModelAdmin
    -0.68
     disambiguazione
    -0.67
    :+:
    -0.66
    #+#
    -0.64
    PYX
    -0.64
    >>()
    -0.62
    kreis
    -0.61
    POSITIVE LOGITS
    
    0.48
     információk
    0.47
    پیوند
    0.46
    طفى
    0.43
    lossians
    0.43
    енье
    0.43
    مني
    0.42
     مرئيه
    0.42
     once
    0.41
    ponge
    0.41
    Activations Density 1.129%

    No Known Activations