© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12986
    Prev
    Next
    INDEX
    Explanations

    words used in blog posts or conversations to describe personal experiences or opinions, especially those related to hobbies, family, or feelings.

    oai_token-act-pair · gemini-2.0-flash

    Personal opinions/experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     right
    -0.61
     Right
    -0.56
    Right
    -0.52
    right
    -0.50
     droite
    -0.48
     Jones
    -0.45
    gráfica
    -0.44
    <bos>
    -0.44
    iedz
    -0.44
     affirmé
    -0.44
    POSITIVE LOGITS
     الحره
    0.76
     nonUne
    0.73
     Wicidata
    0.70
    !")
    0.68
     typelib
    0.65
    parsedMessage
    0.65
    !}
    0.65
    !&
    0.62
     ExecuteAsync
    0.62
    InSection
    0.61
    Activations Density 6.138%

    No Known Activations