© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4298
    Prev
    Next
    INDEX
    Explanations

    place names/location references, especially cities and regions

    oai_token-act-pair · gemini-2.0-flash

    Place names, Organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    #
    -0.71
    <bos>
    -0.68
    penup
    -0.58
    TextWatcher
    -0.55
     disambiguazione
    -0.55
    uilla
    -0.55
     GreatSchools
    -0.54
    UrlEncoded
    -0.50
    voit
    -0.50
     bord
    -0.50
    POSITIVE LOGITS
    CppMethod
    0.56
    atigable
    0.54
     endregion
    0.52
     archipelago
    0.50
     Económica
    0.50
    reggio
    0.50
    ŚĆ
    0.50
     VY
    0.50
    verifyException
    0.49
    pertory
    0.49
    Activations Density 1.229%

    No Known Activations