© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11638
    Prev
    Next
    INDEX
    Explanations

    references to watching TV, especially the show "Breaking Bad", and possibly discussions of the quality of what's being watched.

    oai_token-act-pair · gemini-2.0-flash

    TV and film media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ConstraintMaker
    -0.81
     protoimpl
    -0.79
    parsedMessage
    -0.78
    MemoryWarning
    -0.78
    GraphicsUnit
    -0.77
     pinulongan
    -0.74
     disambiguazione
    -0.73
    RTDA
    -0.73
     كومونز
    -0.72
     kasarigan
    -0.71
    POSITIVE LOGITS
    Paper
    0.41
    ítása
    0.41
     Paper
    0.38
     salariés
    0.38
     Nacionales
    0.36
     prisonniers
    0.36
     masculinos
    0.36
    YMS
    0.36
    auce
    0.35
    ítás
    0.35
    Activations Density 0.495%

    No Known Activations