© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13239
    Prev
    Next
    INDEX
    Explanations

    mentions of TV shows, particularly when discussing ratings or viewership

    oai_token-act-pair · gemini-2.0-flash

    TV shows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     reality
    -1.26
    reality
    -1.04
     Reality
    -1.03
    Reality
    -0.96
     réalité
    -0.85
     realidad
    -0.74
     realities
    -0.74
     realtà
    -0.72
     actuality
    -0.70
     Realität
    -0.68
    POSITIVE LOGITS
     air
    0.69
    air
    0.66
    RegressionTest
    0.65
     SwitchCompat
    0.64
    Coordonnées
    0.61
     airs
    0.60
    ayer
    0.60
    agisse
    0.59
    ništvo
    0.59
     premier
    0.58
    Activations Density 2.627%

    No Known Activations