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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10902
    Prev
    Next
    INDEX
    Explanations

    file path and SQL update commands

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    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
     ","
    -0.59
    ölkerung
    -0.58
    ","
    -0.53
     nature
    -0.53
    gameserver
    -0.51
    änä
    -0.51
    hasErrors
    -0.50
     ','
    -0.50
     thrombosis
    -0.49
    enosis
    -0.48
    POSITIVE LOGITS
     Reſ
    0.64
    ":
    0.60
    ':
    0.59
     Perſ
    0.59
     Anſ
    0.59
    '.
    0.58
     =>
    0.56
     ſte
    0.54
     himſelf
    0.54
     تضيفلها
    0.54
    Activations Density 4.828%

    No Known Activations