© 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. 10224
    Prev
    Next
    INDEX
    Explanations

    code diffs, especially additions, in C-like code

    oai_token-act-pair · gemini-2.0-flash

    @@

    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
     Range
    -0.59
    range
    -0.56
     range
    -0.55
    Range
    -0.51
     De
    -0.50
     Johnson
    -0.49
    kio
    -0.47
    tis
    -0.47
    ran
    -0.47
     Wood
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.92
    GEBURTSDATUM
    0.92
     jsPsych
    0.91
     дописавши
    0.85
     linkovi
    0.83
    DoubleQuotes
    0.81
     disambiguazione
    0.79
     Chwiliwch
    0.79
     oprot
    0.79
    SequentialGroup
    0.78
    Activations Density 3.551%

    No Known Activations