© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 794
    Prev
    Next
    INDEX
    Explanations

    words related to TV shows, especially "The Six Million Dollar Man" and Andre the Giant.

    oai_token-act-pair · gemini-2.0-flash

    professional wrestling

    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
    
    -0.90
    GEBURTSDATUM
    -0.77
     صوتيه
    -0.76
    IBOutlet
    -0.75
    出版年
    -0.74
    IVEREF
    -0.72
     '\\;'
    -0.70
     createState
    -0.66
    MemoryWarning
    -0.65
     Roskov
    -0.63
    POSITIVE LOGITS
     Wink
    0.49
     Lieb
    0.49
     Dink
    0.46
     magasiner
    0.45
     Harlem
    0.43
     Solu
    0.43
    aga
    0.43
    bikini
    0.42
    Sirius
    0.42
     Proof
    0.41
    Activations Density 0.397%

    No Known Activations