© 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. 4836
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical changes and trends

    oai_token-act-pair · gemini-2.0-flash

    increase/decrease

    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
    SequentialGroup
    -0.84
     ModelExpression
    -0.75
    findpost
    -0.59
     ujednoznacz
    -0.59
    +#+#
    -0.58
     שוליים
    -0.57
    !*\
    -0.56
    MENAFN
    -0.53
    subsubsection
    -0.52
     AllAfrica
    -0.52
    POSITIVE LOGITS
     increase
    2.16
    increase
    1.87
     Increase
    1.78
     decrease
    1.78
    Increase
    1.75
     increases
    1.64
     INCREASE
    1.62
    decrease
    1.55
     Decrease
    1.52
     increased
    1.52
    Activations Density 3.442%

    No Known Activations