© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    references to printed publications

    oai_token-act-pair · gemini-2.0-flash

    print

    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
    ξε
    -0.51
    Nationalité
    -0.49
    rupal
    -0.48
    gav
    -0.47
    URLException
    -0.47
     $__
    -0.46
     tịch
    -0.46
    ריאה
    -0.46
    AnimationsModule
    -0.46
    tuous
    -0.45
    POSITIVE LOGITS
     print
    0.74
     imprimi
    0.70
     Print
    0.69
     Administrativna
    0.69
     Prints
    0.65
     printing
    0.65
    printing
    0.63
     Numerade
    0.62
     estimés
    0.61
    Print
    0.60
    Activations Density 5.342%

    No Known Activations