© 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. 3145
    Prev
    Next
    INDEX
    Explanations

    words indicating time, location, or order

    oai_token-act-pair · gemini-2.0-flash

    no

    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
    RetentionPolicy
    -0.68
    +#+#
    -0.66
     disambiguazione
    -0.60
    انيف
    -0.59
    AutoField
    -0.59
     calendriers
    -0.58
     udaler
    -0.57
     Mahomet
    -0.56
     crdi
    -0.54
    TestMethod
    -0.54
    POSITIVE LOGITS
     no
    1.71
    no
    1.23
     kein
    0.96
     keine
    0.96
     geen
    0.94
     нет
    0.94
     NO
    0.94
    No
    0.90
     No
    0.90
     nothing
    0.84
    Activations Density 0.739%

    No Known Activations