© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    references to academic publications

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    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
     myſelf
    -0.92
     chofe
    -0.92
     pleaſure
    -0.83
     Jefus
    -0.82
     doubtnut
    -0.81
    noons
    -0.81
     faſt
    -0.79
     moschino
    -0.78
     Monfieur
    -0.77
     ſind
    -0.77
    POSITIVE LOGITS
     Re
    0.50
     Pot
    0.49
     Co
    0.49
     Sh
    0.47
     Me
    0.47
     Tra
    0.46
     Off
    0.45
     Pro
    0.45
     I
    0.43
     En
    0.43
    Activations Density 0.678%

    No Known Activations