© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3636
    Prev
    Next
    INDEX
    Explanations

    the name of a city/country, followed by related nouns (airport, hotel, driver...)

    oai_token-act-pair · gemini-2.0-flash

    Account information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    RegressionTest
    -0.79
     Мексичка
    -0.79
    adpleegd
    -0.77
    findpost
    -0.75
    setVerticalGroup
    -0.73
    DockStyle
    -0.70
    EndContext
    -0.65
     SafeMath
    -0.65
    TagMode
    -0.65
    ⓧ
    -0.62
    POSITIVE LOGITS
     Cape
    0.49
    YLON
    0.44
     Lanka
    0.44
    Ufficio
    0.42
    ([-
    0.41
    ره
    0.41
    InputTagHelper
    0.41
      (
    0.41
    stellen
    0.40
     صوتيه
    0.40
    Activations Density 0.657%

    No Known Activations